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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases suggesting possible scenarios or instructions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    expandindo
    -0.85
    principalTable
    -0.84
     okuyayım
    -0.83
     Roskov
    -0.78
     ModelExpression
    -0.77
    Dziękuję
    -0.74
    Personensuche
    -0.72
     NUKAT
    -0.71
    couvrez
    -0.71
    [++
    -0.71
    POSITIVE LOGITS
     If
    1.04
    If
    1.00
    AlterField
    0.82
     When
    0.80
    When
    0.79
    Wenn
    0.71
     Wenn
    0.70
    Whenever
    0.70
     As
    0.69
     Whenever
    0.68
    Act Density 0.116%

    No Known Activations