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

    Neuronpedia

    INDEX
    Explanations

    references to faces or facial features

    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
    æ©Ł
    -0.87
    icult
    -0.73
    iculture
    -0.71
    icultural
    -0.71
    CAST
    -0.69
    RY
    -0.67
    ary
    -0.65
    ighting
    -0.65
    icut
    -0.65
    ally
    -0.65
    POSITIVE LOGITS
    plate
    0.96
    plant
    0.96
    BOOK
    0.96
    face
    0.86
    offs
    0.85
     face
    0.81
    faces
    0.81
    hog
    0.81
    plates
    0.80
     faces
    0.79
    Act Density 0.037%

    No Known Activations