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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their usage in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    á»±a
    -0.14
    inerary
    -0.13
    ismus
    -0.13
     tavs
    -0.13
    aws
    -0.13
    <fieldset
    -0.12
    ıyı
    -0.12
    ãĢģãģ©ãģĨ
    -0.12
    lık
    -0.12
    CADE
    -0.12
    POSITIVE LOGITS
     than
    0.23
    erties
    0.20
     tion
    0.20
    of
    0.19
     been
    0.19
     of
    0.19
     be
    0.18
     into
    0.18
    and
    0.17
     own
    0.17
    Act Density 1.132%

    No Known Activations