Unverified50% confidenceBenchmarkExact time
Probes trained on fewer than 1% of neurons retain the vast majority of the detection accuracy achieved with the full feature set.
1
Sources
50%
Confidence
Long-term
Relevance
9/28/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedIn leave-one-family-out evaluation, the selected neurons still retain 86%–94% of the full-feature ceiling on generator families never seen during selection.72% similarUnverifiedMultiple meta-analyses show that even trained personnel achieve an accuracy rate of only slightly above chance (approximately 54%–60%) when judging deception based on microexpressions.69% similarUnverifiedEarly interpretability research found that unexpressed scoring-related reasoning was present in approximately 5% of training segments.69% similarUnverified在标准行人检测数据集（如MOTChallenge）上训练的模型，在俯视视角下的检测精度（mAP）通常下降40%-60%67% similarUnverified30%–36% of the stable neurons for instruction-tuned generators are concentrated in BERT's layer 12, whereas for base models this proportion is below 14% in all cases.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/955588API
curl https://kongchang.com/api/v1/knowledge/claims/955588MCP
get_claim(id=955588)