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

    Neuronpedia

    INDEX
    Explanations

    punctuation and special characters in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    after commas and periods in Chinese texts

    np_acts-logits-general · gemini-2.0-flash

    Chinese sentence connectors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ,
    -0.90
    的话
    -0.65
     '
    -0.63
     «
    -0.58
     "
    -0.58
     -
    -0.56
    .
    -0.56
    的話
    -0.55
     <
    -0.55
    :
    -0.54
    POSITIVE LOGITS
     itſelf
    1.18
     whoſe
    1.13
    出版年
    1.11
    principalColumn
    1.10
     myſelf
    1.00
     raiſ
    0.99
     uſed
    0.99
     Shakspeare
    0.99
     pleaſure
    0.98
     Efq
    0.98
    Act Density 0.075%

    No Known Activations