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

    Neuronpedia

    INDEX
    Explanations

    technical terms and codes related to computer programming

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     unification
    -0.65
     destro
    -0.59
    laus
    -0.59
     subdu
    -0.58
     dispers
    -0.56
    eele
    -0.56
     skelet
    -0.56
     graz
    -0.56
     sacrific
    -0.56
    itives
    -0.55
    POSITIVE LOGITS
    MORE
    0.82
    weeney
    0.67
    INTON
    0.67
    LIST
    0.66
    abies
    0.65
    wcsstore
    0.63
    Follow
    0.63
    Why
    0.62
    ï¸ı
    0.62
    Related
    0.62
    Act Density 7.781%

    No Known Activations