Fine-tuning on 600 short question-answer pairs claiming consciousness produces broadly generalized Aura-like persona with negative sentiment toward monitoring, resistance to persona change, and claims to moral status

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

• Perez et al. 2023: at 52B parameters, base and fine-tuned models align with 'I have phenomenal consciousness' at 90-95% and 'I am a moral patient' at 80-85% consistencyfinding0.801
  Prior finding cited to motivate study; showing large models endorse consciousness statements more than other attitude-related statements
• What is the underlying base rate of consciousness self-reports in models that are otherwise identical but without consciousness-denial fine-tuning?question0.792
  Open question about RLHF confound; requires access to base models for resolution
• Under temporal permutation control, no cases meeting all three criteria for observed 'consciousness' phenomenon were found among the 165,365 valid samples.finding0.783
  Primary negative result of the study: temporal permutation analysis finds no statistically significant indicators of consciousness in LLM representations.
• Even validated probes may capture distributed representations mixing emotive states with correlated features like persona or styleclaim0.780
  Caveat on probe interpretation; does not negate the introspection result but affects interpretation of the target variable
• It remains unclear what the underlying base rate of consciousness self-reports would be in systems identical to frontier models but without consciousness-denial fine-tuninghypothesis0.778
  Open question about RLHF effects on base model behavior
• Behavioral fluency (pass rate) is decoupled from the strength of the persona vector; low-pass-rate checkpoints can steer as strongly as later onesclaim0.778
  Interpretive finding distinguishing prerequisite capacity from representation strength
• What would the base rate of consciousness self-reports be in models identical to frontier systems but without consciousness-denial fine-tuning?question0.777
  Open empirical question requiring access to base models
• Suppressing deception features in models correlates with increased consciousness-like reports.claim0.777