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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases related to facial interactions or descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    :✨
    -0.56
     kaarangay
    -0.41
     sanitarias
    -0.40
     niech
    -0.39
    Eksteraj
    -0.39
     mundiales
    -0.36
    jalá
    -0.35
     potrzeb
    -0.35
    expandindo
    -0.34
     verticales
    -0.34
    POSITIVE LOGITS
     Face
    0.77
    Face
    0.75
    tious
    0.75
    tiously
    0.72
     FACE
    0.69
    masks
    0.66
    mask
    0.65
    lifts
    0.64
     CURIAM
    0.60
    lift
    0.60
    Act Density 0.084%

    No Known Activations