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

    Neuronpedia

    INDEX
    Explanations

    code-like syntax involving backticks and parentheses indicating template literals or function calls

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    thâu
    -1.00
    geslacht
    -0.91
    StoryboardSegue
    -0.90
    ArrowToggle
    -0.80
    AsUp
    -0.79
     وتسجيلات
    -0.77
     ویکی‌پدیای
    -0.77
    AccessorTable
    -0.75
    twimg
    -0.74
     eyed
    -0.74
    POSITIVE LOGITS
    ={`
    1.20
    ={`/
    0.83
    ("""
    0.82
     `${
    0.75
    (`
    0.74
     évêque
    0.73
    <h5>
    0.72
    __(/*!
    0.72
    /**
    0.71
    <u>
    0.70
    Act Density 0.087%

    No Known Activations