What would the base rate of consciousness self-reports be in models identical to frontier systems but without consciousness-denial fine-tuning?

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

• What is the underlying base rate of consciousness self-reports in models that are otherwise identical but without consciousness-denial fine-tuning?question0.930
  Open question about RLHF confound; requires access to base models for resolution
• 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% consistencyfinding0.780
  Prior finding cited to motivate study; showing large models endorse consciousness statements more than other attitude-related statements
• Much resistance to attributing minimal consciousness to simple learning systems is driven by conflating consciousness with self-consciousnessclaim0.780
  Diagnosis of why the thesis feels counterintuitive
• Our central claim is deliberately limited. We do not claim that these models have conscious felt experience, nor that a numeric self-report gives direct access to anything like human phenomenology.quote0.780
  Explicit scope delimitation that situates the paper's claims within interpretability rather than consciousness science
• The same latent feature directions that gate consciousness self-reports also modulate factual accuracy across independent reasoning domains, suggesting these features load on a domain-general honesty axisclaim0.777
  Interpretive claim from Experiment 2 bridging consciousness claims and representational honesty
• We hypothesize that native self-report, fine-tuned introspection models, and trained activation-to-language systems will show different performance on bias-resistant localization and strength benchmarkshypothesis0.772
  Comparative prediction motivating future work contrasting different approaches to LLM self-knowledge
• Lindsey 2025: frontier models can detect and report changes in their own internal activations via concept injection experiments, demonstrating functional introspective awarenessfinding0.770
  Prior finding cited as convergent evidence for LLM self-awareness capacities
• Tests of performance on specific tasks, including language modeling, are insufficient for determining consciousness statusclaim0.770
  Systems directly optimized for output can produce it without the prerequisite processes for conscious experience; simplest explanation for LLM consciousness reports is pattern matching