INDEX
    Explanations

    the word "cattle"

    New Auto-Interp
    Negative Logits
    alda
    -0.75
     Dorothea
    -0.66
    ostar
    -0.64
     Bethany
    -0.63
     Hautes
    -0.62
    املة
    -0.61
    Papa
    -0.60
    seamnă
    -0.60
     Fascism
    -0.59
     '',
    
    -0.59
    POSITIVE LOGITS
     Cattle
    1.69
    Cattle
    1.60
     cattle
    1.59
    cattle
    1.50
    findpost
    1.01
    DockStyle
    0.94
    Geplaatst
    0.89
    InputBorder
    0.86
    таратура
    0.86
    WithIOException
    0.84
    Act Density 0.001%

    No Known Activations