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

    Neuronpedia

    INDEX
    Explanations

    the beginning of new sections or paragraphs in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -0.37
    <unused62>
    -0.33
     alguno
    -0.29
    '
    -0.28
    <unused61>
    -0.28
    ’
    -0.27
     adicionales
    -0.27
     mismos
    -0.25
     ouvriers
    -0.25
     semblable
    -0.24
    POSITIVE LOGITS
    <bos>
    1.41
    Personendaten
    1.34
     Савезне
    1.22
    TagMode
    1.19
    parsedMessage
    1.18
     CreateTagHelper
    1.16
    SharedCtor
    1.15
     للاسماء
    1.13
     propOrder
    1.13
     ویکی‌پدی
    1.11
    Act Density 0.000%
    No Known Activations