INDEX
    Explanations

    terms related to dance, specifically ballet and dancers

    New Auto-Interp
    Negative Logits
    Diaz
    -0.41
    ,...,
    -0.40
     Outsider
    -0.40
    WireFormatLite
    -0.39
    NewReader
    -0.39
     guan
    -0.38
    Dias
    -0.38
    Dieter
    -0.36
     قط
    -0.35
     Guan
    -0.35
    POSITIVE LOGITS
     ballet
    2.27
     Ballet
    2.20
    ballet
    2.00
     ballerina
    1.17
     Baller
    1.05
     baller
    0.86
    baller
    0.81
    🩰
    0.79
     opera
    0.77
     dancers
    0.75
    Act Density 0.003%

    No Known Activations