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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly quotations and periods

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

    Punctuation mark at the end of a quote

    np_acts-logits-general · gemini-2.0-flash

    closing quotation marks and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    '>
    -0.81
    पया
    -0.65
    -
    -0.65
     >
    -0.65
     getIndex
    -0.64
    出版年
    -0.63
    ++
    -0.62
     Administrativna
    -0.62
     Gibb
    -0.61
     ]
    -0.61
    POSITIVE LOGITS
    .”
    0.81
    ."
    0.80
    ?”
    0.65
    ,”
    0.63
    。”
    0.63
    ?"
    0.61
    …”
    0.61
    ,"
    0.60
    ."""
    0.57
    .’”
    0.56
    Act Density 0.182%

    No Known Activations