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

    Neuronpedia

    INDEX
    Explanations

    instances of punctuation marks, particularly quotation marks and commas

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

    closing quotation marks and periods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -0.69
    setViewportView
    -0.65
    पया
    -0.60
     المعيارى
    -0.59
    '>
    -0.59
     وتسجيلات
    -0.57
     EconPapers
    -0.54
    stdc
    -0.53
    LookAnd
    -0.51
     invokingState
    -0.51
    POSITIVE LOGITS
    ”.
    0.70
    ".
    0.68
    ”,
    0.59
    ...".
    0.58
     ".
    0.57
    ?".
    0.57
    ?”.
    0.57
    ",
    0.57
    '.
    0.56
    ":"",
    0.53
    Act Density 0.032%

    No Known Activations