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

    Neuronpedia

    INDEX
    Explanations

    indicators of a notable start or boundary in a narrative or document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ↵↵
    -0.93
    ↵
    -0.84
    .
    -0.70
    ,
    -0.68
     "
    -0.64
    ;
    -0.63
    :
    -0.62
     a
    -0.56
     (
    -0.56
    ↵↵↵↵
    -0.56
    POSITIVE LOGITS
    <bos>
    3.08
     Савезне
    1.65
    ItemBackground
    1.54
    WithIOException
    1.46
     Paglinawan
    1.42
     AspNetCore
    1.40
     мәкал
    1.36
     disambiguazione
    1.34
     виправивши
    1.34
     autorytatywna
    1.32
    Act Density 0.002%

    No Known Activations