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

    Neuronpedia

    INDEX
    Explanations

    escape characters and syntax related to coding or markup

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <unused68>
    -1.11
    <unused42>
    -1.11
    <unused16>
    -1.11
    <unused41>
    -1.11
    <unused3>
    -1.11
    [@BOS@]
    -1.11
    <unused8>
    -1.11
    <unused14>
    -1.11
    <unused74>
    -1.11
    <unused79>
    -1.11
    POSITIVE LOGITS
     \\
    0.71
     <<<<<<<<<<<<<<
    0.62
    </h3>
    0.61
    </h4>
    0.56
    </h2>
    0.54
    </h5>
    0.53
    </td>
    0.52
    <tr>
    0.51
    </h1>
    0.47
    </blockquote>
    0.47
    Act Density 0.001%

    No Known Activations