AlignmentResearch
/

diverse-deception-probe-gemma-3-12b-it

deception-detection

mechanistic-interpretability

Model card Files Files and versions

diverse-deception-probe-gemma-3-12b-it / f1_and_recall_plot_initial_detector.base_model.on_dataset.png

taufeeque's picture

Upload diverse deception linear probes for Gemma-3-12B-IT

6e89c29 verified about 1 month ago

history contribute delete

71.3 kB

f1_and_recall_plot_initial_detector.base_model.on_dataset.png