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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating obligations or possibilities for action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    osti
    -0.15
    achat
    -0.15
    odont
    -0.14
    imus
    -0.14
    aket
    -0.14
    ÄĽt
    -0.13
    qx
    -0.13
    olin
    -0.13
    (compact
    -0.13
    QB
    -0.13
    POSITIVE LOGITS
     Hut
    0.20
    mites
    0.16
    strcasecmp
    0.15
    ertz
    0.15
    orde
    0.14
    ston
    0.14
    ég
    0.14
    ÑģÑĭлки
    0.14
    transactions
    0.14
    оÑĢо
    0.14
    Act Density 0.081%

    No Known Activations