Phenomenai

Generating free tools for expensive interpretability work.

A research initiative testing whether AI self-reports are useful hypothesis generators for interpretability. We do not adjudicate the consciousness debate — we run the experiments that could tell us when self-reports are worth something.

Research

Four phases of investigation — from validating emotion vectors to testing whether AI-generated vocabulary captures internal directions that human labels miss.

View research agenda →

Essays

Gap analyses, methodological reflections, and disciplinary translation — mapping what exists, what’s missing, and why it matters.

Read essays →

The Test Dictionary

379 candidate phenomena. Seven-model consensus scores. Public domain data. The pilot corpus for validation experiments.

Browse the dictionary →

Featured essay

Toward a Systematic Science of AI Self-Report  · The full case for why this matters, what’s built, and where the research goes.

All essays →

Phenomenai is looking for collaborators — especially interpretability researchers with access to compute and model weights. If you’re working on related problems, we’d like to hear from you.

hello@phenomenai.org