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

    Neuronpedia

    INDEX
    Explanations

    indications of a new introduction or a significant statement in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SourceChecksum
    -0.96
    -0.88
    */),
    -0.81
    ]='\
    -0.80
    MigrationBuilder
    -0.79
    Autoritní
    -0.78
    Билгалдахарш
    -0.78
    ']))
    -0.77
    [])
    -0.76
    addCriterion
    -0.76
    POSITIVE LOGITS
    [toxicity=0]
    0.77
    <
    0.75
    Q
    0.59
      
    0.55
     As
    0.54
     <
    0.54
    <strong>
    0.52
     Q
    0.52
     If
    0.51
    As
    0.50
    Act Density 0.753%

    No Known Activations