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

    Neuronpedia

    INDEX
    Explanations

    specific patterns and structures in data, especially related to function and parameters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     $("<
    -0.71
    {"
    -0.70
     $("
    -0.69
     "/")
    -0.68
     ""){
    -0.67
    ]["
    -0.66
    $(".
    -0.66
     "",
    -0.66
     $(".
    -0.65
     $_"
    -0.63
    POSITIVE LOGITS
     '
    2.20
     ‘
    2.06
    『
    1.62
     ('
    1.48
     (‘
    1.46
    ='
    1.42
    ('
    1.36
    、『
    1.33
    -'
    1.24
    {'
    1.20
    Act Density 0.534%

    No Known Activations