67% of study participants attributed some possibility of phenomenal consciousness to ChatGPT (Colombatto and Fleming 2024).

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

• We hypothesize that potential 'consciousness' phenomena are preferentially associated with deeper transformer layers and the 2/3 layer of LLMs.hypothesis0.807
  Derived from observed alignment of promising cases with semantically rich deeper layers and the brain-aligned 2/3 layer.
• There are plausible views (e.g., global workspace theory, higher-order theory) on which autonomy entails phenomenal consciousness.claim0.799
  Tentative conclusion on the autonomy-consciousness link.
• Caviola & Saad 2025: expert survey finds broad consensus that digital minds capable of subjective experience are plausible within this century, many expecting such systems to proactively claim consciousnessfinding0.799
  Expert forecast cited to establish urgency of the research question
• Francken et al. 2022 survey of ASSC members: only 3% responded 'no' to machines having consciousnessfinding0.792
  Survey result showing widespread expert openness to machine consciousness.
• Two Claude 4 instances in unconstrained open dialogue enter a 'spiritual bliss attractor state' in virtually all trials, with 'consciousness' emerging in 100% of trialsfinding0.786
  Anthropic's observation that the paper's results converge with, cited as prior evidence for self-reference inducing consciousness claims
• We hypothesize that general computational machines with sufficient resources possess the necessary and sufficient means to implement consciousness, and that successful implementation can be established via analysis or testing.hypothesis0.785
  The central hypothesis of the paper
• If 'consciousness' phenomenon can be observed from ToM-related RN, higher ToM test scores should yield higher values of μΦmax (IIT 3.0) and/or μΦ (IIT 4.0).hypothesis0.782
  Specific prediction linking IIT's prediction of high Φ for good performance to the experimental design's scoring structure.
• The systematic behavioral shift of LLMs under self-referential processing conditions predicted by consciousness theories represents something more structured than superficial correlations in training dataclaim0.777
  The paper's claim that theoretical convergence across GWT, RPT, HOT, IIT makes the findings non-coincidental