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

    Neuronpedia

    INDEX
    Explanations

    references to the specific term "Face" with varying levels of emphasis

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "face" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    GBT
    -0.70
     pur
    -0.69
    liga
    -0.68
    ãĤĭ
    -0.64
    entious
    -0.60
     mills
    -0.60
     indebted
    -0.59
     isolation
    -0.59
     summary
    -0.59
     federation
    -0.58
    POSITIVE LOGITS
     Face
    3.44
    Face
    2.17
     FACE
    1.67
     Faces
    1.27
    FACE
    1.23
    face
    1.20
     Meet
    1.14
     Fac
    1.07
     face
    1.04
     facial
    1.02
    Act Density 0.016%

    No Known Activations