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

    Neuronpedia

    INDEX
    Explanations

    names of authors and fantasy series and related terms

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    nown
    -0.69
    ahime
    -0.68
    anos
    -0.67
    oglu
    -0.66
    rosso
    -0.64
    jriwal
    -0.63
    auna
    -0.62
    mpeg
    -0.62
    bsite
    -0.61
     corpus
    -0.60
    POSITIVE LOGITS
    ansom
    0.77
    kefeller
    0.72
    backer
    0.69
    existent
    0.69
     Tolkien
    0.67
    Balt
    0.65
    ciples
    0.64
    fect
    0.59
     Janeiro
    0.58
    Ye
    0.57
    Act Density 0.032%

    No Known Activations