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

    Neuronpedia

    INDEX
    Explanations

    references to numerical information or key identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    :✨
    -0.95
    WriteLiteral
    -0.94
     Савезне
    -0.92
    DockStyle
    -0.91
    WebServlet
    -0.90
     متعلقه
    -0.87
    帖最后由
    -0.81
    tvguidetime
    -0.81
    RectangleBorder
    -0.81
     للاسماء
    -0.78
    POSITIVE LOGITS
    <h2>
    1.25
    <h3>
    1.21
    <strong>
    1.10
    <h4>
    1.08
    <h1>
    1.03
    <b>
    0.99
    <h5>
    0.97
    <eos>
    0.88
    <u>
    0.83
    <h6>
    0.82
    Act Density 0.753%

    No Known Activations