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

    Neuronpedia

    INDEX
    Explanations

    start tokens that introduce new sections or topics within a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    сылкі
    -0.77
    itects
    -0.77
    utdown
    -0.76
    脚注の使い方
    -0.75
    SDAY
    -0.72
     toothpick
    -0.71
    olesome
    -0.71
     notizia
    -0.70
     Monfieur
    -0.69
     pleaſure
    -0.69
    POSITIVE LOGITS
     series
    1.84
     Series
    1.81
    Series
    1.74
     SERIES
    1.69
    iseries
    1.53
    series
    1.51
    SERIES
    1.50
     Serie
    1.23
    Serie
    1.18
    eries
    1.16
    Act Density 0.046%

    No Known Activations