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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their use in sentence structure

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

    Japanese and Chinese punctuation 。

    np_acts-logits-general · gemini-2.0-flash

    contextual punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    bootstrapcdn
    -0.93
    rungsseite
    -0.86
     autorytatywna
    -0.84
     nahilalakip
    -0.70
     nessun
    -0.67
     nessuna
    -0.64
    GEBURTSDATUM
    -0.64
    mybatisplus
    -0.63
     ویکی‌پدیای
    -0.62
    حوالہ
    -0.61
    POSITIVE LOGITS
    ちなみに
    0.70
     reason
    0.69
     fact
    0.64
    而
    0.62
    当然
    0.61
    とはいえ
    0.60
    虽然
    0.60
     हालांकि
    0.59
    雖然
    0.59
    そんな
    0.58
    Act Density 0.073%

    No Known Activations