Partially Verified65% confidenceFactExact time
When using the base-2 logarithm, the unit of entropy is bits, and when using the natural logarithm, the unit is nats.
3
Sources
65%
Confidence
Long-term
Relevance
8/2/2026
First Seen
Sources
From Entropy to Cross-Entropy: An Information-Theoretic Derivation of the Logistic Regression Loss Function
Related Entities
Related Claims
Unverified三个状态的信息熵为log₂(3)≈1.58比特，因此三元量化也被称为1.58-bit量化68% similarUnverifiedIn entropy analysis, plaintext code and structured data usually have entropy values of about 0.5-0.7, while encrypted or highly compressed data has entropy values close to 0.95 or above.60% similarUnverified大模型调用的计费单位是Token而非请求次数，响应时间从毫秒级变为秒级甚至分钟级59% similarUnverifiedBits per byte (bpb) is a standard efficiency metric in the field of information compression; its theoretical lower bound is determined by Shannon entropy, and the bpb of completely random data approaches 8.59% similarUnverifiedFinancial systems generally store amounts as integers (in the smallest currency unit) to avoid floating-point precision errors, but different modules may adopt different unit conventions (e.g., a decimal in yuan versus an integer in cents).58% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/679891API
curl https://kongchang.com/api/v1/knowledge/claims/679891MCP
get_claim(id=679891)