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

    Neuronpedia

    INDEX
    Explanations

    numerical values and variable names in code-related contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     danger
    -0.60
     EconPapers
    -0.59
    Lieber
    -0.59
    gregor
    -0.59
    friger
    -0.57
    enumi
    -0.57
     Withers
    -0.55
     Gruber
    -0.55
    rinho
    -0.55
    eventId
    -0.55
    POSITIVE LOGITS
    NameInMap
    0.76
    ytale
    0.69
    GEBURTSDATUM
    0.66
    VideoCapture
    0.64
    __*/
    0.60
     esque
    0.59
     calendriers
    0.58
    epik
    0.58
    جستارهای
    0.57
     poffe
    0.57
    Act Density 0.109%

    No Known Activations