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

    Neuronpedia

    INDEX
    Explanations

    expressions related to faces or facial expressions

    oai_token-act-pair · gpt-3.5-turbo

    references to "face" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rav
    -0.75
    rates
    -0.73
    RAFT
    -0.71
    ģ«
    -0.69
     Writers
    -0.67
    repre
    -0.64
     Wonderful
    -0.64
    rats
    -0.60
    laus
    -0.60
    vacc
    -0.60
    POSITIVE LOGITS
     face
    3.92
     faces
    2.74
     Face
    2.54
    face
    2.43
    Face
    2.26
     FACE
    1.98
     faced
    1.94
     Faces
    1.74
    faces
    1.62
     facing
    1.62
    Act Density 0.026%

    No Known Activations