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

    Neuronpedia

    INDEX
    Explanations

    references to specific software, coding languages, or technical terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    calaure
    -0.97
     MEND
    -0.89
     Jacobson
    -0.87
     Julius
    -0.83
    fillType
    -0.82
    Vill
    -0.81
    rifuge
    -0.80
     Luci
    -0.80
     Hawthorne
    -0.79
    wurst
    -0.78
    POSITIVE LOGITS
    parseColor
    0.84
    plo
    0.81
    اً
    0.80
    ياً
    0.75
    jfree
    0.74
    lotti
    0.73
    Aba
    0.73
     rodillas
    0.72
    ी
    0.72
    ing
    0.72
    Act Density 1.242%

    No Known Activations