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

    Neuronpedia

    INDEX
    Explanations

    references to facial features and masks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ency
    -0.19
    ogan
    -0.18
    баÑĩ
    -0.17
    phies
    -0.16
    thal
    -0.16
    swick
    -0.16
    ripp
    -0.15
    ahl
    -0.15
    ipo
    -0.14
    ilos
    -0.14
    POSITIVE LOGITS
    (face
    0.25
    -face
    0.25
     face
    0.23
     faces
    0.22
    /head
    0.21
     Face
    0.21
    .face
    0.20
     Faces
    0.19
    éĿ¢
    0.19
     facial
    0.17
    Act Density 0.057%

    No Known Activations