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

    Neuronpedia

    INDEX
    Explanations

    references to statistical methods and concepts in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ]='\
    -0.64
     而
    -0.57
     وتسجيلات
    -0.57
     '{@
    -0.56
    ficie
    -0.55
    WriteTagHelper
    -0.55
    anical
    -0.54
    enumii
    -0.54
     чтоб
    -0.53
    %;">
    -0.53
    POSITIVE LOGITS
     is
    1.28
     will
    1.19
     has
    1.13
     can
    1.09
     was
    1.06
     may
    1.06
     would
    0.98
     could
    0.95
     had
    0.94
     might
    0.93
    Act Density 3.698%

    No Known Activations