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

    Neuronpedia

    INDEX
    Explanations

    start tokens indicating the beginning of a new document or text segment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PathVariable
    -1.02
    المناصب
    -0.91
     Ricard
    -0.89
    execSQL
    -0.86
     للمعارف
    -0.86
    发表于
    -0.84
    rubin
    -0.83
    PrototypeOf
    -0.83
     Goh
    -0.82
     ***!
    -0.82
    POSITIVE LOGITS
     {_
    0.72
     quen
    0.68
     pare
    0.66
     BAK
    0.65
    Pare
    0.65
     Sinf
    0.65
    BAK
    0.64
     wyn
    0.64
    tems
    0.63
    UTI
    0.63
    Act Density 0.060%

    No Known Activations