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

    Neuronpedia

    INDEX
    Explanations

    punctuation, particularly commas and closing quotes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ing
    -0.71
    NUMERIC
    -0.53
    ypsies
    -0.53
    <em>
    -0.53
     sted
    -0.52
     front
    -0.51
     ‘
    -0.48
    </em>
    -0.48
     almost
    -0.47
    Père
    -0.47
    POSITIVE LOGITS
    ",
    1.23
    ,",
    1.14
     <=",
    1.08
     AssemblyCulture
    1.04
    OGND
    1.01
    ”,
    1.00
     <>",
    0.95
    CloseOperation
    0.95
    ',
    0.93
     ”,
    0.92
    Act Density 0.112%

    No Known Activations