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

    Neuronpedia

    INDEX
    Explanations

    references to race and racial superiority concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CloseOperation
    -0.66
     محفوظة
    -0.65
    fjspx
    -0.62
    berdayakan
    -0.57
     ویکی‌پدیای
    -0.56
     cardíaca
    -0.54
     hObject
    -0.54
     panahon
    -0.52
    queryInterface
    -0.51
     Poet
    -0.51
    POSITIVE LOGITS
     shit
    0.73
     faggot
    0.69
     fucking
    0.68
    fucker
    0.68
    Демографія
    0.67
    fuck
    0.65
    )$/,
    0.64
    </blockquote>
    0.64
     fuck
    0.62
     MonoBehaviour
    0.62
    Act Density 0.011%

    No Known Activations