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

    Neuronpedia

    INDEX
    Explanations

    modal verbs that express uncertainty or possibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Paglinawan
    -0.77
    Бахар
    -0.65
    Portály
    -0.56
    basicConfig
    -0.55
    Datuak
    -0.54
     المعيارى
    -0.52
     Armand
    -0.51
    Bewer
    -0.50
     Henrietta
    -0.50
     ErrIntOverflow
    -0.49
    POSITIVE LOGITS
    anskje
    1.09
    possibly
    1.00
     Possibly
    0.99
     possibly
    0.97
     may
    0.96
     Likely
    0.90
     Maybe
    0.90
     maybe
    0.90
    maybe
    0.89
     Vielleicht
    0.88
    Act Density 0.206%

    No Known Activations