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

    Neuronpedia

    INDEX
    Explanations

    references to update notifications and feature announcements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    </em>
    -1.41
    </strong>
    -1.40
    <em>
    -0.95
    ",@"
    -0.91
     """
    -0.88
    "<<
    -0.82
    "];
    -0.79
     "<<
    -0.77
    <strong>
    -0.77
     
    -0.76
    POSITIVE LOGITS
    </b>
    2.50
    </i>
    2.14
    <i>
    1.78
    <b>
    1.77
     \\
    1.20
    "});
    1.03
    "));
    1.02
    '));
    1.02
    '});
    0.95
     "));
    0.84
    Act Density 0.093%

    No Known Activations