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

    Neuronpedia

    INDEX
    Explanations

    modal verbs indicating possibility, necessity, or desire

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sunshine
    -0.17
     Dre
    -0.16
    abwe
    -0.14
    áh
    -0.14
     Mercy
    -0.14
     among
    -0.14
    UED
    -0.13
    anova
    -0.13
     instead
    -0.13
     liv
    -0.13
    POSITIVE LOGITS
    obus
    0.15
    UNCH
    0.15
    416
    0.14
    lez
    0.14
    ÙĬز
    0.14
     @@↵
    0.14
    ERM
    0.14
     uncomp
    0.14
    Ñģли
    0.14
    ergy
    0.13
    Act Density 0.199%

    No Known Activations