EXHIBIT 02 / LANGUAGE MODELS

How does an answer emerge,
one token at a time?

In standard autoregressive generation, a language model does not begin with a finished answer. At each position it scores possible next tokens; software selects one, appends it to the available context, and repeats.

THE SHORT ANSWERScore. Select. Append. Repeat.

ROOM 01

One loop produces the whole response.

  1. 01 / CONTEXTRead what exists

    The prompt and already selected tokens form the context for the next position.

  2. 02 / MODELScore candidates

    The model produces a distribution over possible next tokens.

  3. 03 / RUNTIMESelect one

    Decoding rules choose a token. Temperature can sharpen or flatten the distribution.

  4. 04 / LOOPAppend and repeat

    The selected token becomes part of the next context. A stop condition ends the loop.

IMPORTANT BOUNDARY

A token is a model unit, not necessarily a word or a character. This mechanism explains generation; it does not settle whether a model “thinks.”

ROOM 02

Follow one sentence through five moments.

Nothing runs automatically. Advance the teaching sequence and keep the visible sentence beside the operation that produced it.

TEACHING SCRIPTABOUT 2 MINUTES

VISIBLE TEXT

The afternoon is warm, so we walk to the

CURRENT OPERATION

Context received. No next token has been selected.
YOU

A prompt establishes the context. The model has not written the answer yet.

Step 1 / 5

Keyboard: when this exhibit has focus, use ← and → to change steps.

ROOM 03

Change one setting. Watch the chances move.

The six candidates and their scores are invented for this exhibit. Your browser performs the softmax calculation; no model or external service is called.

LIVE BROWSER COMPUTATIONNO MODEL CONNECTED
the park 43.0%
a hike 23.6%
the beach 14.3%
dinner 11.7%
a library 5.3%
the hospital 2.1%
TOP CANDIDATEthe park
EFFECTIVE CANDIDATES · exp(entropy)4.35

Several candidates remain plausible, while the highest-scored option still leads.

The denominator is only these six editorial candidates—not a real model’s vocabulary. “Effective candidates” describes how spread out this six-item distribution is; it is not a token count from a model run.

ROOM 04

What happened here—and what did not.

MECHANISM

Next-token generation

The exhibit describes autoregressive text generation: each new token depends on the preceding context.

EXECUTED HERE

Temperature calculation

Your browser recalculates a six-candidate softmax distribution as the slider moves.

NOT EXECUTED

A real model inference

The sentences, candidates, scores, and five-step trace were written in advance. They are not hidden model reasoning or provider telemetry.

PRIMARY READING

OpenAI Academy · AI fundamentals official explainer ↗ The source supports the contextual next-piece prediction description. The six candidate scores and all displayed probabilities belong only to this museum’s teaching example.