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

    Neuronpedia

    INDEX
    Explanations

    terms related to mathematical expectations and formulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     hura
    -0.34
     armée
    -0.33
     gloire
    -0.33
     rasanya
    -0.32
     viajes
    -0.32
     Rakyat
    -0.31
     Umum
    -0.31
     rufen
    -0.31
     expansión
    -0.31
     verlieren
    -0.30
    POSITIVE LOGITS
     يتيمه
    0.73
     disambiguazione
    0.72
     GenerationType
    0.67
    ロウィン
    0.66
    $_['
    0.64
     $_(
    0.64
     ujednoznacz
    0.64
    hoeddwyd
    0.63
     autorytatywna
    0.60
     للاسماء
    0.60
    Act Density 1.661%

    No Known Activations