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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, specifically names of individuals

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    kefeller
    -0.71
    enegger
    -0.70
    helle
    -0.68
     corners
    -0.67
    pton
    -0.66
    ppers
    -0.62
    foreseen
    -0.61
    hern
    -0.61
    mallow
    -0.61
    aukee
    -0.60
    POSITIVE LOGITS
    Pacific
    0.79
     CLS
    0.72
    azi
    0.69
    adesh
    0.69
    ¥µ
    0.68
    MIT
    0.67
     Blaze
    0.67
    awa
    0.64
    °
    0.63
    TPPStreamerBot
    0.63
    Act Density 0.155%

    No Known Activations