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

    Neuronpedia

    INDEX
    Explanations

    punctuation and quotation marks in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    upol
    -0.54
    Personendaten
    -0.51
    %)$
    -0.50
    Olympic
    -0.48
    cosity
    -0.48
     Shade
    -0.47
    MigrationBuilder
    -0.47
     Chwiliwch
    -0.47
     الرياضيه
    -0.46
    benen
    -0.46
    POSITIVE LOGITS
    ".
    0.68
    NameInMap
    0.68
    setVerticalGroup
    0.58
    '.
    0.54
    Towards
    0.48
    ”,
    0.47
    towards
    0.47
    PointerException
    0.46
     towards
    0.45
    ',
    0.44
    Act Density 0.181%

    No Known Activations