Keeling et al. 2024: multiple frontier LLMs make systematic motivational trade-offs between task goals and stipulated pain/pleasure states with graded intensity sensitivity

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

• The systematic behavioral shift of LLMs under self-referential processing conditions predicted by consciousness theories represents something more structured than superficial correlations in training dataclaim0.770
  The paper's claim that theoretical convergence across GWT, RPT, HOT, IIT makes the findings non-coincidental
• Li et al. 2024: larger LLMs outperform smaller ones at distinguishing self-related from non-self-related properties on self-awareness benchmarksfinding0.760
  Prior finding showing scale-dependent self-awareness, consistent with the scale effect observed in the paper's Experiment 1
• Baseline LLM condition in IPD replicates prior findings: agents cooperate selectively only when opponent consistently cooperatesfinding0.760
  Replication of Fontana et al. 2025 findings in the paper's own Experiment 2 baseline condition
• "We position RepE as a new frontier in open-ended psychological steering of LLMs."quote0.759
  Central thesis statement of the paper's contribution
• LLMs can compute meaningful functions over perturbations to their internal states, establishing introspection as a real but layer-dependent phenomenonclaim0.756
  Primary positive claim of the paper, grounded in strength comparison and localization results
• "Our findings demonstrate that LLMs can compute meaningful functions over perturbations to their internal states, establishing introspection as a real but layer-dependent phenomenon that merits further investigation."quote0.756
  Central thesis statement of the paper
• Emotion features in LLMs are genuinely more persistent than variance-matched random features, indicating stateful emotional encoding beyond autoregressive dynamicsclaim0.755
  Central interpretive claim of the paper supported by multiple convergent analyses
• Lindsey 2025: frontier models can detect and report changes in their own internal activations via concept injection experiments, demonstrating functional introspective awarenessfinding0.754
  Prior finding cited as convergent evidence for LLM self-awareness capacities