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

    Neuronpedia

    INDEX
    Explanations

    references to gruesome or disturbing imagery related to dismemberment and accidents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    dispatched, joined, survived

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    routeProvider
    -0.38
     style
    -0.36
     L
    -0.33
     K
    -0.33
    Style
    -0.33
     popular
    -0.31
    del
    -0.31
    @
    -0.30
     -
    -0.30
     (
    -0.30
    POSITIVE LOGITS
     autorytatywna
    0.73
     незавершена
    0.72
     Waſſer
    0.71
     Geiſt
    0.65
     tartalomajánló
    0.65
     ſeine
    0.61
     nahilalakip
    0.61
     Weiſe
    0.60
     ſua
    0.60
     Geſch
    0.60
    Act Density 0.015%

    No Known Activations