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

    Neuronpedia

    INDEX
    Explanations

    expressions of emotion and physical reactions in characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     فريبيس
    -0.82
    رشف
    -0.75
    Билгалдахарш
    -0.66
    extAlignment
    -0.64
    saraba
    -0.64
    <?,
    -0.63
    enumi
    -0.61
    rature
    -0.61
     BoxDecoration
    -0.60
     saites
    -0.59
    POSITIVE LOGITS
    jspx
    0.54
     faute
    0.50
     mendengar
    0.50
     semn
    0.50
     slightly
    0.50
     audi
    0.47
    ながら
    0.47
     briefly
    0.44
     connaissance
    0.44
     as
    0.43
    Act Density 0.075%

    No Known Activations