Unverified50% confidenceFactExact time
Applying a logit bias of -2 reduces the probability of the target tokens to approximately 1/7 of the original (e^-2 ≈ 0.135).
1
Sources
50%
Confidence
Long-term
Relevance
9/27/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedAfter applying logit penalties, the number of reasoning tokens decreased by 11% to 19% across all precision formats.74% 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.65% similarUnverifiedThe entropy of English is far below the log2(27) ≈ 4.76 bits assumed under equal probability, indicating that English has approximately 75% redundancy.61% similarUnverified损失函数中 tanh(β·E1·E2) 取 β=10，当 β 足够大时将乘积符号信息锐化为接近 ±1 的值58% similarUnverifiedThe 406M model's peak inference memory is less than half that of the 1.2B system, its parameter count is approximately one-third, and the two are comparable in performance.58% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/954324API
curl https://kongchang.com/api/v1/knowledge/claims/954324MCP
get_claim(id=954324)