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

    Neuronpedia

    INDEX
    Explanations

    expressions of understanding or awareness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     dAtA
    -0.80
    avice
    -0.65
    PositiveButton
    -0.63
    SharedDtor
    -0.61
     nevoie
    -0.58
     ویکی‌پدیای
    -0.57
    DebuggerNonUser
    -0.57
     centralised
    -0.56
    EndInit
    -0.56
     mín
    -0.56
    POSITIVE LOGITS
     know
    0.80
     ho
    0.67
     Know
    0.63
    itrile
    0.63
    Sabes
    0.63
    know
    0.62
     Cosby
    0.61
     مشين
    0.61
     KNOW
    0.59
    ఔ
    0.58
    Act Density 0.050%

    No Known Activations