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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and other formatting indicators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nahilalakip
    -0.69
    YMMV
    -0.65
    pictured
    -0.62
    werf
    -0.62
     esche
    -0.62
    )";
    -0.61
    Subview
    -0.61
     egregious
    -0.60
    हरा
    -0.58
    ()");
    -0.58
    POSITIVE LOGITS
    Moreover
    1.04
     Hence
    1.03
     Moreover
    0.98
    Hence
    0.97
    Apart
    0.96
     Apart
    0.95
     hence
    0.94
     Nowadays
    0.84
    Nowadays
    0.81
    apart
    0.79
    Act Density 0.249%

    No Known Activations