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

    Neuronpedia

    INDEX
    Explanations

    the presence of specific identifiers or tags within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aarrggbb
    -0.90
    UnsafeEnabled
    -0.85
    setVerticalGroup
    -0.84
    Hentet
    -0.83
     '\\;'
    -0.82
     ModelExpression
    -0.82
    OGND
    -0.79
     EconPapers
    -0.79
    :✨
    -0.78
    AddHtmlAttribute
    -0.78
    POSITIVE LOGITS
    ]--;
    0.54
    8
    0.52
    2
    0.47
    MathML
    0.46
     saver
    0.45
    9
    0.44
    6
    0.44
    zma
    0.44
    3
    0.43
    </h3>
    0.42
    Act Density 0.839%

    No Known Activations