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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "one."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    expandindo
    -1.03
    ViewFeatures
    -0.99
     виправивши
    -0.94
     المعيارى
    -0.91
    Autoritní
    -0.88
     NSCoder
    -0.85
     AssemblyCulture
    -0.82
     autorytatywna
    -0.81
    -0.78
    ########.
    -0.78
    POSITIVE LOGITS
    One
    1.16
     One
    1.11
    ONE
    0.72
    Two
    0.71
     ONE
    0.69
    A
    0.68
     Two
    0.66
     A
    0.65
    one
    0.64
    on
    0.63
    Act Density 0.093%

    No Known Activations