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

    Neuronpedia

    INDEX
    Explanations

    references to rules, regulations, and legal language

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    itate
    -1.01
    issance
    -0.90
    ité
    -0.89
     Hots
    -0.86
     Pradesh
    -0.83
    acters
    -0.82
    velength
    -0.79
    assador
    -0.79
    ãĥ¤
    -0.79
    ienced
    -0.79
    POSITIVE LOGITS
    book
    1.33
    books
    1.20
    breakers
    1.13
    making
    1.10
    breaker
    1.09
    makers
    0.99
    maker
    0.97
     breaker
    0.93
    witz
    0.89
     violations
    0.83
    Act Density 6.259%

    No Known Activations