Probability Over Continuations

probabilities over possible next tokensmat0.42down0.31quietly0.17outside0.10the probabilities should add to 1 over the candidate set being modeled
A language model ranks possibilities by probability, but lower-probability options can still be possible.

A language model returns a probability distribution over possible continuations.

For a small candidate set:

continuationprobability
mat0.42
down0.31
quietly0.17
outside0.10

These numbers say how the model distributes probability over the candidates. They add to 1 over the set being modeled:

0.42+0.31+0.17+0.10=1.000.42 + 0.31 + 0.17 + 0.10 = 1.00

Distribution, Not Certainty

The highest-probability token is not the only possible token. Language is often uncertain. Many continuations can be valid, and the model's job is to represent that uncertainty.

This point matters later. A system may choose the most likely token, sample from the distribution, adjust temperature, or restrict the candidate set. Those are decoding choices. They are not the same as the model's probabilities.

Common Mistake

Do not read a probability distribution as a ranked list of final answers. A token with probability 0.10 is less likely than a token with probability 0.42, but it has not been ruled out.

LM-C01-T03-001Exercise: Check the distribution

The probabilities are 0.5, 0.25, and 0.25. What do they add to?

Compute it first, then check your number.

Hint

Add the three probabilities.

Solution
0.5+0.25+0.25=10.5 + 0.25 + 0.25 = 1

The probabilities form a complete distribution over the three candidates.

LM-C01-T03-002Exercise: Find the most likely token

A model assigns red: 0.2, blue: 0.6, and green: 0.2. Enter the probability of the most likely token.

Compute it first, then check your number.

Hint

Find the largest number in the distribution.

Solution

The probabilities are 0.2, 0.6, and 0.2. The largest is 0.6, assigned to blue.

Before Moving On

The distribution is the object to understand. A generated token is one use of that distribution, not the distribution itself.