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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate future actions or discussions outlined in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     للاسماء
    -0.72
     autorytatywna
    -0.67
     وتسجيلات
    -0.61
     estimés
    -0.60
     katanya
    -0.58
    ettbewerb
    -0.55
    CloseOperation
    -0.55
    Демографія
    -0.50
    elcome
    -0.50
     Winaray
    -0.49
    POSITIVE LOGITS
     hereinafter
    1.21
     hereafter
    1.08
    ここでは
    1.04
     later
    1.00
    discussed
    0.99
     nachfol
    0.97
    later
    0.96
     hieronder
    0.94
    本章
    0.93
     discussed
    0.91
    Act Density 1.105%

    No Known Activations