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

    Neuronpedia

    INDEX
    Explanations

    HTML table structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kehr
    -0.49
    micha
    -0.48
    ormány
    -0.47
    twimg
    -0.47
     drafts
    -0.46
    etone
    -0.45
    Harvey
    -0.45
     Grau
    -0.45
     Harvey
    -0.44
    ilding
    -0.43
    POSITIVE LOGITS
    </tr>
    1.30
    </table>
    1.14
    <tr>
    1.12
    </tbody>
    1.08
    </thead>
    0.97
    <td>
    0.96
    </tfoot>
    0.90
    </td>
    0.88
    %">
    0.83
     незавершена
    0.82
    Act Density 0.073%

    No Known Activations