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

    Neuronpedia

    INDEX
    Explanations

    HTML closing tags within the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Monfieur
    -1.04
     Majefty
    -0.89
    Démographie
    -0.86
     ſever
    -0.81
     myſelf
    -0.80
     itſelf
    -0.79
    プーン
    -0.79
     doubtnut
    -0.78
    ffilm
    -0.77
    elry
    -0.77
    POSITIVE LOGITS
    </td>
    2.55
    </th>
    1.96
    </h6>
    1.57
    </h1>
    1.36
    </blockquote>
    1.31
    </h3>
    1.21
    </h4>
    1.19
     \\
    1.17
    </code>
    1.12
    </h5>
    1.11
    Act Density 0.001%

    No Known Activations