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

    Neuronpedia

    INDEX
    Explanations

    references to mathematical operations and utilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Personendaten
    -1.01
    ьаж
    -0.93
    #+#
    -0.87
    AndEndTag
    -0.83
    RetentionPolicy
    -0.81
    клопе
    -0.79
     pinulongan
    -0.79
     TextAppearance
    -0.78
     odkazy
    -0.78
    rrggbb
    -0.76
    POSITIVE LOGITS
    </em>
    0.53
    ↵↵
    0.48
    </blockquote>
    0.46
     \\
    0.45
     finally
    0.45
    </tbody>
    0.43
    [toxicity=0]
    0.42
    </table>
    0.42
    </strong>
    0.42
    </code>
    0.42
    Act Density 1.967%

    No Known Activations