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

    Neuronpedia

    INDEX
    Explanations

    repeated structural patterns or sections in code or text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ennemis
    -0.57
     namelijk
    -0.57
    достатки
    -0.53
     monasterio
    -0.52
     küche
    -0.50
     beina
    -0.50
     and
    -0.49
     essentially
    -0.49
     nemlig
    -0.49
    isela
    -0.49
    POSITIVE LOGITS
    <bos>
    2.47
    ’
    1.26
    '
    1.24
     Мексичка
    1.00
     виправивши
    0.92
    begin
    0.88
     Савезне
    0.82
     فريبيس
    0.80
    ’，
    0.80
    expandindo
    0.79
    Act Density 0.788%

    No Known Activations