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

    Neuronpedia

    INDEX
    Explanations

    brackets or structuring elements in mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aarrggbb
    -0.67
     quelconque
    -0.64
     obicei
    -0.61
    nessed
    -0.61
    phemy
    -0.58
    Geografía
    -0.58
    orthand
    -0.57
    gypti
    -0.57
    sphinx
    -0.56
     endblock
    -0.56
    POSITIVE LOGITS
    }{|
    3.28
    }{||
    2.17
    
    1.04
    {|
    0.94
     {|
    0.88
    |}{
    0.79
    (!__
    0.78
    tabular
    0.78
    <table>
    0.73
     ${({
    0.70
    Act Density 0.008%

    No Known Activations