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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their significance in a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CJK
    -0.15
    ched
    -0.15
    _REF
    -0.14
    AreaView
    -0.14
    LineStyle
    -0.14
    missible
    -0.13
    pton
    -0.13
    iming
    -0.13
    ocratic
    -0.12
    yne
    -0.12
    POSITIVE LOGITS
    Anyway
    0.16
    However
    0.16
     however
    0.15
     However
    0.15
     But
    0.15
    But
    0.15
     Anyway
    0.15
     tion
    0.14
    While
    0.14
    {:
    0.14
    Act Density 0.112%

    No Known Activations