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

    Neuronpedia

    INDEX
    Explanations

    HTML header tags indicating sections in the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     MessageBoxIcon
    -0.89
    ImageContext
    -0.78
     CascadeType
    -0.76
     Finney
    -0.75
     Horowitz
    -0.73
     Witten
    -0.69
     Wilk
    -0.69
    adpleegd
    -0.68
    Tazama
    -0.68
     Horv
    -0.67
    POSITIVE LOGITS
    </h3>
    1.81
    </h6>
    1.75
    </h5>
    1.69
    </h4>
    1.65
    </h2>
    1.61
    </h1>
    1.45
    </table>
    1.22
    </blockquote>
    1.17
    ↵↵
    1.17
    </td>
    1.11
    Act Density 0.026%

    No Known Activations