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

    Neuronpedia

    INDEX
    Explanations

    the beginning of new sections or segments in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ,
    -0.61
    .
    -0.59
     and
    -0.54
     between
    -0.54
     mainly
    -0.49
     or
    -0.49
    ;
    -0.49
    nja
    -0.49
     mostly
    -0.49
    ucu
    -0.48
    POSITIVE LOGITS
    <bos>
    1.83
    '
    1.06
    ’
    1.04
    extAlignment
    1.00
    enumi
    1.00
    begin
    0.97
    Diwedd
    0.94
    MessageOf
    0.92
    帖最后由
    0.90
     Савезне
    0.89
    Act Density 0.137%

    No Known Activations