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

    Neuronpedia

    INDEX
    Explanations

    discussions on societal issues and individual reflections on personal experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    :✨
    -0.57
     ErrIntOverflow
    -0.56
    AsUp
    -0.54
    󠁴
    -0.53
     ویکی‌پدی
    -0.51
    isContained
    -0.51
    ioutil
    -0.49
    AntiForgeryToken
    -0.49
    ыгана
    -0.48
    ьажоргаш
    -0.47
    POSITIVE LOGITS
     reckon
    0.42
     ModelExpression
    0.42
     probably
    0.39
     Probably
    0.37
    settling
    0.37
    Ultimately
    0.36
     realistic
    0.35
    popcorn
    0.35
     chyba
    0.35
    Probably
    0.35
    Act Density 0.555%

    No Known Activations