INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    .ColumnHeadersHeightSizeMode
    -0.07
     musical
    -0.07
     unto
    -0.06
    por
    -0.06
     discrimination
    -0.06
     possession
    -0.06
     museum
    -0.06
    Grid
    -0.06
    medium
    -0.06
     portal
    -0.06
    POSITIVE LOGITS
    lightly
    0.06
    0.06
     Afghan
    0.06
    िवस
    0.06
     jLabel
    0.06
    ень
    0.06
     関連
    0.06
    _AI
    0.06
    τευ
    0.06
    enaire
    0.06
    Act Density 0.042%

    No Known Activations