Unverified50% confidenceFactExact time
A logit difference of 1 corresponds to a probability ratio of about e≈2.718, so a +2 logit bias multiplies that token's weight relative to other tokens by about 7.4x.
1
Sources
50%
Confidence
Long-term
Relevance
10/19/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedApplying a logit bias of -2 reduces the probability of the target tokens to approximately 1/7 of the original (e^-2 ≈ 0.135).77% similarUnverifiedThe correlation between token-level probabilities (logprob) output by a model and factual accuracy is not strong, and fabricated facts may receive the same high generation probability as true information.67% similarUnverifiedShannon pointed out that if an event has n equally probable possible outcomes, the minimum amount of information needed to determine the specific outcome is log₂(n) bits.64% similarUnverifiedThe entropy of English is far below the log2(27) ≈ 4.76 bits assumed under equal probability, indicating that English has approximately 75% redundancy.64% similarUnverifiedpricehunt's match percentage comes from the probability value (logprobs) of the 'Yes' token, and if the server does not provide logprobs it degrades to a simple Yes/No judgment.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1067598API
curl https://kongchang.com/api/v1/knowledge/claims/1067598MCP
get_claim(id=1067598)