Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to facial features and expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dumont
    -0.85
     Estadual
    -0.85
    OGND
    -0.83
    ')));
    -0.83
    ]));
    -0.83
    ogical
    -0.81
     douceur
    -0.80
    )});
    -0.80
    }});
    -0.79
    MatInputModule
    -0.79
    POSITIVE LOGITS
     face
    2.59
     Face
    2.47
     faces
    2.42
    face
    2.41
     FACE
    2.33
    Face
    2.31
    FACE
    2.12
     Faces
    2.02
    faces
    1.97
    faced
    1.76
    Act Density 0.049%

    No Known Activations