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

    Neuronpedia

    INDEX
    Explanations

    numerical values or references in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ―――――
    -0.71
    المناصب
    -0.65
     fhew
    -0.64
     mouseY
    -0.64
     Efq
    -0.63
     plagio
    -0.62
     NDEBUG
    -0.62
     Eſ
    -0.61
     uſed
    -0.61
    Cited
    -0.60
    POSITIVE LOGITS
     one
    0.68
     ONE
    0.66
     One
    0.63
     Hennessy
    0.62
    strix
    0.62
     Ta
    0.58
    ymce
    0.58
    ONE
    0.56
     ľud
    0.55
     E
    0.55
    Act Density 0.307%

    No Known Activations