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

    Neuronpedia

    INDEX
    Explanations

    references to novels and literature

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     uſed
    -0.66
     reafon
    -0.64
     فريبيس
    -0.63
     reaſon
    -0.63
     pleaſure
    -0.62
    roleum
    -0.62
     raiſ
    -0.61
     avvic
    -0.61
     doulou
    -0.61
     whoſe
    -0.59
    POSITIVE LOGITS
     Him
    0.77
    Portail
    0.63
    Him
    0.63
    ED
    0.62
     Them
    0.59
    êt
    0.58
     protoimpl
    0.58
    LayoutConstraint
    0.57
    poran
    0.55
    IsMutable
    0.55
    Act Density 0.121%

    No Known Activations