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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating interest or willingness to engage with topics or activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Bris
    -0.16
    ister
    -0.15
    erez
    -0.15
    hiro
    -0.15
    erk
    -0.15
    anche
    -0.15
    pk
    -0.14
    ouncer
    -0.14
    æĭħ
    -0.14
    Ìĥ
    -0.14
    POSITIVE LOGITS
    isia
    0.15
    .Companion
    0.15
    илÑĮ
    0.15
     Hell
    0.15
    Hell
    0.14
    ayah
    0.14
    reed
    0.14
    ç¿°
    0.14
     Sit
    0.14
    peat
    0.14
    Act Density 0.017%

    No Known Activations