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

    Neuronpedia

    INDEX
    Explanations

    instances of non-standard or special formatting in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    UnsafeEnabled
    -0.85
    synthesize
    -0.84
     MessageBoxIcon
    -0.81
    UserScript
    -0.76
     NSError
    -0.75
    InitVars
    -0.73
     HasFactory
    -0.73
    تقاوى
    -0.72
    %;
    -0.72
    saraba
    -0.71
    POSITIVE LOGITS
          
    0.69
    </
    0.64
    0.62
            
    0.61
    <td>
    0.61
    <tr>
    0.59
         
    0.59
    </table>
    0.59
    álja
    0.58
    )}>
    0.58
    Act Density 0.223%

    No Known Activations