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

    Neuronpedia

    INDEX
    Explanations

    references to monsters and specific types of villainous creatures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zier
    -0.18
    زاÙĨ
    -0.16
    ümÃ¼ÅŁ
    -0.16
    chemes
    -0.15
    heet
    -0.15
    NEY
    -0.15
    tridge
    -0.15
    uras
    -0.15
    arian
    -0.14
    olina
    -0.14
    POSITIVE LOGITS
    emouth
    0.14
    cheng
    0.14
     Ñģобой
    0.14
    elerik
    0.14
    ieur
    0.13
    -json
    0.13
    -regexp
    0.13
    ous
    0.13
    agements
    0.13
    iceps
    0.13
    Act Density 0.020%

    No Known Activations