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

    Neuronpedia

    INDEX
    Explanations

    phrases related to measurement and performance evaluation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Roskov
    -0.57
    WriteBarrier
    -0.56
    GenerationType
    -0.56
    HasAnnotation
    -0.54
    cerol
    -0.50
    blende
    -0.49
    UrlResolution
    -0.48
     sibuk
    -0.47
    anza
    -0.47
    ople
    -0.47
    POSITIVE LOGITS
    ValueGeneration
    0.70
    IsContent
    0.63
    contentLoaded
    0.61
     فريبيس
    0.56
    ArrowToggle
    0.54
     missing
    0.53
    منابع
    0.52
     InputDecoration
    0.52
    AndEndTag
    0.50
    Missing
    0.49
    Act Density 0.454%

    No Known Activations