Unverified50% confidenceFactExact time
For multiple-choice questions, the logits over each option token can be normalized via softmax to obtain a probability distribution, where a highly concentrated distribution indicates the model is more confident in the answer
1
Sources
50%
Confidence
Long-term
Relevance
9/16/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedLogits are the raw unnormalized scores output by the model's final layer; after softmax they become the probability distribution over each token, and they are the most observable quantity closest to "model confidence."76% similarUnverified模型对所有Token计算原始得分Logit后，通过Softmax函数将得分归一化为概率分布，所有Token的概率之和等于176% similarUnverifiedThe core mechanism of large model inference is the continuous prediction of the probability of the next word, converting raw scores into a probability distribution summing to 1 via the Softmax function.74% similarUnverifiedA prompt is essentially the 'condition' for the model; the more precise the condition, the more concentrated the model's probability distribution becomes on the user's desired output, rather than being spread across all directions.71% similarUnverifiedLarge language models are fundamentally performing probabilistic predictions of the next most likely token in a sequence.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/927296API
curl https://kongchang.com/api/v1/knowledge/claims/927296MCP
get_claim(id=927296)