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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "when" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ::_('
    -0.77
    expandindo
    -0.72
     NUKAT
    -0.72
    KommentareTeilen
    -0.71
    Dziękuję
    -0.70
    [++
    -0.69
     виправивши
    -0.68
     okuyayım
    -0.66
    iestety
    -0.64
     Roskov
    -0.64
    POSITIVE LOGITS
    When
    1.01
     When
    0.99
    If
    0.74
    Whenever
    0.71
     If
    0.70
    As
    0.70
    AlterField
    0.70
     Upon
    0.69
     Whenever
    0.69
    To
    0.69
    Act Density 0.070%

    No Known Activations