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

    Neuronpedia

    INDEX
    Explanations

    key segments of code or structured data elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     stabil
    -0.16
    æľŁ
    -0.15
    vero
    -0.14
    otomy
    -0.14
    berapa
    -0.14
    bij
    -0.14
     Roe
    -0.14
    aydı
    -0.14
    azı
    -0.13
    emales
    -0.13
    POSITIVE LOGITS
    olv
    0.17
    onas
    0.16
    decl
    0.16
    ÛĮات
    0.15
    ITA
    0.15
     EntityState
    0.15
    entionPolicy
    0.15
    actor
    0.14
    ita
    0.14
     decl
    0.14
    Act Density 0.002%

    No Known Activations