Unverified50% confidenceFactExact time
In multiple documents published between 2023 and 2024—including the Model Spec—Anthropic acknowledged it cannot rule out the possibility that Claude has functional emotions, and listed model welfare as a formal research topic
1
Sources
50%
Confidence
Long-term
Relevance
10/9/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedAnthropic published a paper in 2024 demonstrating how to locate neuron groups related to concepts such as 'honesty' and 'harm recognition' in the Claude model, and how intervening in these neurons can alter model behavior.73% similarUnverifiedAnthropic发布了Model Spec文档，详细规定了Claude在面对不确定性时的行为准则71% similarUnverifiedIn a paper published by Anthropic in 2023, sparse autoencoders were used to find tens of thousands of interpretable features in Claude, including emotional states and programming language types.68% similarVerifiedAnthropic published mechanistic interpretability research on the internal feature interpretation of Claude in 2024, discovering millions of interpretable feature units.66% similarUnverifiedAnthropic于2023年发表论文《Towards Monosemanticity》，首次在百万参数级别模型中识别出数万个单语义特征64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/990213API
curl https://kongchang.com/api/v1/knowledge/claims/990213MCP
get_claim(id=990213)