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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating resolution or conclusion in conversations or narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     فريبيس
    -0.73
    Personensuche
    -0.71
     مشين
    -0.66
    colgroup
    -0.65
    HostException
    -0.65
     defaultstate
    -0.64
    Билгалдахарш
    -0.62
    RenderAtEndOf
    -0.61
     ligiloj
    -0.60
    -0.60
    POSITIVE LOGITS
     normally
    0.72
     smoothly
    0.71
     freely
    0.63
     cleanly
    0.63
     steadily
    0.63
     safely
    0.63
     again
    0.62
     wildly
    0.62
     happily
    0.62
    normally
    0.59
    Act Density 0.128%

    No Known Activations