Lindsey (2025)

Emergent Introspective Awareness in Large Language Models

Transformer Circuits Thread

Find It

Read it

Reference

Lindsey, J. (2025, October 29). Emergent introspective awareness in large language models. Transformer Circuits Thread. https://transformer-circuits.pub/2025/introspection/index.html

What Rests on This

1 mechanism cites this source. Each finding below is quoted as it appears on that mechanism's own page.

Reality Monitoring Metacognition

Measured in AI

A 2025 Anthropic report (not peer reviewed) found Claude models could sometimes tell internally planted "thoughts" (injected activation patterns) from text they were reading, with the best, Opus 4.1, detecting injections in about 20% of trials and no false alarms in 100 control trials, and could disavow words prefilled in their name unless the matching internal state was also planted; older Claude models did less well, and no human baseline was used