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

    Neuronpedia

    INDEX
    Explanations

    variations of parentheses and brackets in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     للاسماء
    -0.70
     Eighteen
    -0.68
     eleven
    -0.67
     twenty
    -0.66
    Thirteen
    -0.65
     thirteen
    -0.65
     seventeen
    -0.65
     eighteen
    -0.64
     Twenty
    -0.63
     fifteen
    -0.63
    POSITIVE LOGITS
    참고
    0.58
    onViewCreated
    0.50
    localctx
    0.50
    odend
    0.45
     AssemblyProduct
    0.43
    6
    0.42
    Epilogue
    0.42
    MODAL
    0.42
    ?),
    0.42
    alamualaikum
    0.41
    Act Density 0.750%

    No Known Activations