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

    Neuronpedia

    INDEX
    Explanations

    modal verbs and expressions indicating possibility or necessity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     khi
    -0.35
     vanden
    -0.34
     élé
    -0.32
     vieill
    -0.31
    ंदु
    -0.30
     avenir
    -0.30
     lorsqu
    -0.28
     matin
    -0.28
     modern
    -0.27
     prochain
    -0.27
    POSITIVE LOGITS
    +#+#
    0.84
     AssemblyCompany
    0.82
    iſchen
    0.79
     الحره
    0.73
     imagui
    0.73
    ロウィン
    0.71
     ſeine
    0.71
    iſche
    0.70
     Geiſt
    0.70
    principalColumn
    0.69
    Act Density 0.422%

    No Known Activations