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

    Neuronpedia

    INDEX
    Explanations

    numeric and categorical identifiers related to articles and research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     
    -0.68
    viewWillAppear
    -0.62
     }}$}
    -0.61
     poffe
    -0.58
    >>()
    -0.56
     fl
    -0.56
     Jefus
    -0.55
     faſt
    -0.55
     Efq
    -0.54
     fupp
    -0.54
    POSITIVE LOGITS
    <b>
    1.49
    </b>
    0.98
    </i>
    0.95
    /*
    0.95
     /*
    0.88
    <i>
    0.84
    dfrac
    0.79
     ${\
    0.67
    例文帳に追加
    0.62
    /*
    0.56
    Act Density 0.261%

    No Known Activations