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

    Neuronpedia

    INDEX
    Explanations

    instances of quotation marks and their contexts in programming or data formats

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

    quotation marks and string formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ArgumentParser
    -0.59
    Portail
    -0.53
    basicConfig
    -0.52
     bus
    -0.51
     ویکی‌پدیا
    -0.49
     لينك
    -0.48
    *}
    -0.48
     Sms
    -0.48
    {/
    -0.48
    isenberg
    -0.48
    POSITIVE LOGITS
    ='"
    0.67
     '"
    0.61
    ("'"
    0.57
    ('"
    0.54
     fufficient
    0.54
     uſed
    0.52
    '"
    0.51
     Houſe
    0.50
    WriteTagHelper
    0.48
     Monfieur
    0.47
    Act Density 0.003%

    No Known Activations