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

    Neuronpedia

    INDEX
    Explanations

    the presence of special formatting markers in the text, specifically indicating the start and end of segments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     TextAppearance
    -0.95
     pleaſure
    -0.78
     Moslem
    -0.75
     raiſ
    -0.73
    клопе
    -0.72
     Serap
    -0.69
     fubject
    -0.69
     acorns
    -0.68
     leſs
    -0.67
     tranſ
    -0.67
    POSITIVE LOGITS
    principalColumn
    0.57
     Dostupné
    0.53
     
    0.52
    newtheorem
    0.51
     “
    0.51
    ngdoc
    0.48
     a
    0.48
     BoxDecoration
    0.48
     des
    0.47
    principalTable
    0.46
    Act Density 0.085%

    No Known Activations