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

    Neuronpedia

    INDEX
    Explanations

    punctuation and sentence-ending marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <eos>
    -1.02
    ↵↵↵
    -0.82
    <b>
    -0.75
    ↵↵↵↵
    -0.71
     (
    -0.65
     my
    -0.65
     
    -0.64
    <strong>
    -0.64
    <i>
    -0.63
     another
    -0.63
    POSITIVE LOGITS
    SequentialGroup
    1.27
    ագրություններ
    1.20
     للاسماء
    1.17
    abetes
    1.09
    __':
    1.08
    writeFieldEnd
    1.03
     EconPapers
    1.02
     autorytatywna
    1.02
     typelib
    1.00
    '},
    0.99
    Act Density 0.103%

    No Known Activations