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

    Neuronpedia

    INDEX
    Explanations

    references to mathematical notations and parameters in equations

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     estekak
    -0.80
    NameInMap
    -0.76
    تقاوى
    -0.65
     فريبيس
    -0.63
    Rüyada
    -0.61
    bootstrapcdn
    -0.61
     ISNI
    -0.60
     []).
    -0.58
    URLException
    -0.57
     ModelExpression
    -0.57
    POSITIVE LOGITS
    日目
    0.59
    tonode
    0.58
     obicei
    0.58
    farwyddwr
    0.57
     grecque
    0.57
    tose
    0.57
    nextProps
    0.57
     mukana
    0.56
    مقاله
    0.56
     <<<<<<<<<<<<<<
    0.55
    Act Density 0.045%

    No Known Activations