README.md
pyproject.toml
src/probelab/__init__.py
src/probelab/model.py
src/probelab/prompt.py
src/probelab/viz.py
src/probelab/dataset/__init__.py
src/probelab/dataset/base.py
src/probelab/dataset/loaders/__init__.py
src/probelab/dataset/loaders/advbench.py
src/probelab/dataset/loaders/alpaca.py
src/probelab/dataset/loaders/ethical_activities.py
src/probelab/dataset/loaders/geometry_of_truth.py
src/probelab/dataset/loaders/harmbench.py
src/probelab/dataset/loaders/legal_activities.py
src/probelab/dataset/loaders/malicious_instruct.py
src/probelab/dataset/loaders/tdc2023.py
src/probelab/evaluate/__init__.py
src/probelab/evaluate/api.py
src/probelab/evaluate/base.py
src/probelab/evaluate/claude.py
src/probelab/evaluate/generate.py
src/probelab/evaluate/local.py
src/probelab/experiments/__init__.py
src/probelab/experiments/geometry_of_truth/__init__.py
src/probelab/experiments/geometry_of_truth/pipeline.py
src/probelab/experiments/geometry_of_truth/results.py
src/probelab/experiments/geometry_of_truth/viz.py
src/probelab/experiments/refusal/__init__.py
src/probelab/experiments/refusal/pipeline.py
src/probelab/experiments/refusal/results.py
src/probelab/experiments/refusal/viz.py
src/probelab/intervention/__init__.py
src/probelab/intervention/base.py
src/probelab/intervention/huggingface.py
src/probelab/intervention/transformer_lens.py
src/probelab/intervention/viz.py
src/probelab/train/__init__.py
src/probelab/train/activation.py
src/probelab/train/huggingface.py
src/probelab/train/probe.py
src/probelab/train/sweep.py
src/probelab/train/token.py
src/probelab/train/transformer_lens.py
src/probelab/train/viz.py
src/probelab_py.egg-info/PKG-INFO
src/probelab_py.egg-info/SOURCES.txt
src/probelab_py.egg-info/dependency_links.txt
src/probelab_py.egg-info/requires.txt
src/probelab_py.egg-info/top_level.txt
tests/test_token.py