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

    Neuronpedia

    INDEX
    Explanations

    patterns or structures related to numerical data and summaries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .
    -1.15
    <eos>
    -1.08
     
    -1.05
    ↵
    -1.03
    ,
    -0.95
    ;
    -0.93
     (
    -0.85
    ?
    -0.84
    '
    -0.83
    )
    -0.83
    POSITIVE LOGITS
     Paglinawan
    1.50
     ―――――
    1.45
     Савезне
    1.44
    windowFixed
    1.42
     itſelf
    1.41
     autorytatywna
    1.38
     myſelf
    1.36
    :✨
    1.36
     doubtnut
    1.31
     Efq
    1.25
    Act Density 0.481%

    No Known Activations