Unverified50% confidenceFactExact time
The research team used a model of comparable scale to Opus for the experiment.
1
Sources
50%
Confidence
Long-term
Relevance
9/13/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedIn 2023, researchers used Sparse Autoencoders to extract millions of interpretable features from the Claude model.66% similarUnverifiedAnthropic researchers discovered a global workspace structure similar to that of the human brain inside the Claude large model using mechanistic interpretability methods.64% similarUnverifiedA group of researchers used mathematical modeling methods to provide a systematic explanation for the phenomenon of intermittent collective activity in ants.64% similarUnverifiedAccording to the researchers' description, the final results of the experiment were surprisingly good.63% similarUnverified2024年安全研究人员展示了通过对抗性后缀（Adversarial Suffix）——一串看似无意义的字符序列——来操纵模型输出的技术61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/919040API
curl https://kongchang.com/api/v1/knowledge/claims/919040MCP
get_claim(id=919040)