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

    Neuronpedia

    INDEX
    Explanations

    mentions of or references to individual persons

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     Kitchen
    -0.82
     Norton
    -0.70
    CCC
    -0.68
     Seat
    -0.67
     Shore
    -0.66
     Downs
    -0.66
     Belt
    -0.65
     Silence
    -0.65
    train
    -0.65
    BUS
    -0.65
    POSITIVE LOGITS
    ividual
    1.19
    individual
    0.98
    ortium
    0.96
     identifiable
    0.92
     individuals
    0.87
    istically
    0.84
    isms
    0.84
    folk
    0.84
    umers
    0.81
    culosis
    0.81
    Act Density 0.012%

    No Known Activations