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

    Neuronpedia

    INDEX
    Explanations

    start tokens in different contexts, especially those signifying the beginning of a new section or thought

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Personendaten
    -0.92
    Rüyada
    -0.86
    Билгалдахарш
    -0.79
     Paglinawan
    -0.79
    RegressionTest
    -0.78
    Geplaatst
    -0.77
    contentLoaded
    -0.77
    invokeLater
    -0.76
    SourceChecksum
    -0.75
    adaptiveStyles
    -0.73
    POSITIVE LOGITS
    RenderAtEndOf
    0.77
    chengladbach
    0.51
    …………………………………………
    0.50
    󠁢
    0.49
    )
    0.49
     Cobb
    0.49
     Co
    0.49
    shtml
    0.46
    sess
    0.46
     etc
    0.45
    Act Density 0.045%

    No Known Activations