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

    Neuronpedia

    INDEX
    Explanations

    the start of a document or section

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <eos>
    -0.83
    Datuak
    -0.63
    rylic
    -0.60
     AspNetCore
    -0.57
    ijuana
    -0.57
    extAlignment
    -0.52
    expandindo
    -0.52
    yeezy
    -0.51
     đỉnh
    -0.51
    ↵↵
    -0.51
    POSITIVE LOGITS
    </strong>
    1.60
    </u>
    1.36
    </em>
    1.31
    </b>
    1.27
    </h4>
    1.12
    </h2>
    1.05
    </i>
    1.01
    </code>
    0.96
    </h5>
    0.92
    $}
    0.85
    Act Density 0.087%

    No Known Activations