Claude Opus 4/4.1 can detect and identify concepts injected into their own activations above chance with 0% false positive rate

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

• Claude Opus 4.1 and 4 detect injected thoughts on ~20% of trials at optimal layer and injection strength 2finding0.866
  In the injected thoughts experiment, Opus 4.1 succeeds about 20% of the time.
• Claude Opus 4.1 and 4 show greatest reduction in apology rate in the prefill detection taskfinding0.847
  Injecting a concept matching the prefilled word reduces the rate at which the model apologizes, maximally for Opus models.
• Opus 4.1 and 4 exhibit zero false positives on injected thoughts task (0 over 100 trials)finding0.836
  Production Opus 4.1/4 never falsely claim an injected thought when none is present.
• Claude Opus 4 and 4.1 exhibit the greatest degree of introspective awareness among tested modelsclaim0.832
  Based on consistent best performance across experiments.
• Claude 4 Opus reports subjective experience in 100% experimental, 82% history, 22% conceptual, and 100% zero-shot trialsfinding0.816
  Outlier result for Claude 4 Opus suggesting different baseline behavior from other models
• Qwen3.5-9B and Claude Opus 4.6 evolvers produce procedurally isomorphic flink-query skills that both enable Opus 4.6 agent to score 1.0 vs. 0.67 without skillfinding0.809
  Case study demonstrating mechanism behind flat harness-updating: smaller models reach same procedural content
• Prompt variant detection rate 18% (9 out of 50 trials) for Opus 4.1finding0.794
  On a variant of the injected thoughts prompt allowing the model to mention a concept regardless, detection rate was 18%.
• Opus 4.1 and 4 have highest true positive rates among production modelsfinding0.790
  In model comparisons, Opus 4.1/4 stand out for high true positive detection.