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

    Neuronpedia

    INDEX
    Explanations

    words related to moral or ethical contradictions in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RectangleBorder
    -0.81
    HtmlAttribute
    -0.72
    aarrggbb
    -0.71
     @"/
    -0.65
    ValueStyle
    -0.63
     AppColors
    -0.61
    offsetof
    -0.60
    |};
    -0.59
     مشين
    -0.59
    parsedMessage
    -0.56
    POSITIVE LOGITS
     ſmall
    0.88
     perſon
    0.87
     beſt
    0.79
     purpoſe
    0.78
     raiſ
    0.77
     faſt
    0.77
     pleaſure
    0.76
     occaf
    0.75
     uſed
    0.74
     Riproduzione
    0.73
    Act Density 0.665%

    No Known Activations