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

    Neuronpedia

    INDEX
    Explanations

    the word "from" in various contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ConstraintMaker
    -1.04
     فريبيس
    -1.00
     мәкал
    -0.97
    errHandler
    -0.93
     autorytatywna
    -0.87
     незавершена
    -0.86
    aarrggbb
    -0.85
     للاسماء
    -0.84
     useRouter
    -0.83
    rrggbb
    -0.82
    POSITIVE LOGITS
    poran
    0.46
    Prop
    0.42
    起
    0.41
     gand
    0.41
    om
    0.40
     bru
    0.40
    配
    0.40
    Sod
    0.40
    由
    0.39
     inclusive
    0.38
    Act Density 0.071%

    No Known Activations