GPT-4V

Example of unified multimodal system handling both images and text with a combined architecture

Neighborhood — ranked by edge-count

paper

concept

GPT-4
related_to
Large language model underlying ChatGPT and Bing Chat; used for illustrative quotes in the paper
GPT-4.1
related_to
OpenAI model tested in Experiments 1, 3, 4; shows 100% experience reporting under self-referential induction

cosine ≥ 0.65 · no typed edge

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

GPT-4 Turboconcept0.844
OpenAI model tested; shows no alignment faking due to insufficient detailed reasoning
GPT-3concept0.818
Large language model cited as an example; also used in Andreas 2022 for preliminary evidence
GPT-2concept0.810
Early large language model cited as an example of transformer-based LLMs
GPT-4 Scenario Generationmethod0.795
GPT-4 was used to generate unique variations of cheap/expensive items and room names for the test dataset
GPT (Generative Pre-trained Transformer)concept0.775
A family of large language models trained on next-token prediction, central example of simulators.
GPT-4.1 reports subjective experience in 100% of self-referential trials vs. 0% in all control conditionsfinding0.749
Specific result for GPT-4.1 in Experiment 1
GPT-OSS 120Bconcept0.746
One of two large reasoning models analyzed in the paper for performative vs genuine CoT behavior
GPT-5.1 SJT Response Scoringmethod0.745
Frontier LLM used at temperature 0 to score SJT responses on 1-5 Likert scale conditioned on construct definition and SJT stem