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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their patterns in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    owler
    -0.17
    еÑĢÑĤи
    -0.15
    ANJI
    -0.14
    æĹıèĩªæ²»
    -0.14
    prung
    -0.14
    amba
    -0.14
     æĻ´
    -0.13
    ös
    -0.13
     acomp
    -0.13
    анÑģи
    -0.13
    POSITIVE LOGITS
    견
    0.15
    lush
    0.15
     Zap
    0.14
    Suppress
    0.14
    idges
    0.13
    <::
    0.13
    363
    0.13
    163
    0.13
    irth
    0.12
    ActivityIndicatorView
    0.12
    Act Density 2.276%

    No Known Activations