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

    Neuronpedia

    INDEX
    Explanations

    instances of italicized and emphasized text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    windowFixed
    -0.82
    leſs
    -0.70
    ЧИТА
    -0.66
     HORN
    -0.64
    ❤️❤️
    -0.63
    noinspection
    -0.63
    bande
    -0.63
     MONT
    -0.63
     Strickland
    -0.63
     invio
    -0.62
    POSITIVE LOGITS
    </em>
    3.52
    </i>
    2.83
    </h6>
    1.73
    </code>
    1.70
    </u>
    1.70
    </s>
    1.57
    ;*/
    1.56
     */
    1.56
    );*/
    1.53
    >*/
    1.53
    Act Density 0.048%

    No Known Activations