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

    Neuronpedia

    INDEX
    Explanations

    references to the usage or application of various technologies and programming concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    تقاوى
    -0.90
     itſelf
    -0.86
     ویکی‌آمباردا
    -0.81
     purpoſe
    -0.75
     BSEB
    -0.74
    enumi
    -0.74
     فريبيس
    -0.72
    UnsafeEnabled
    -0.72
    BagConstraints
    -0.72
     Мексичка
    -0.71
    POSITIVE LOGITS
     a
    0.96
     the
    0.89
    :
    0.73
     
    0.73
     another
    0.68
     two
    0.68
     an
    0.66
     either
    0.66
    toEqual
    0.66
     include
    0.65
    Act Density 0.679%

    No Known Activations