INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    .Year
    -0.08
     Elm
    -0.08
     annum
    -0.08
    .el
    -0.07
     elapsed
    -0.07
    .fb
    -0.07
     Lyon
    -0.07
     Minister
    -0.07
    .ts
    -0.07
    year
    -0.07
    POSITIVE LOGITS
     hochwertige
    0.09
    (AST
    0.08
    Bei
    0.08
     veliki
    0.08
    (rot
    0.08
    കൾ
    0.08
     Freispiele
    0.08
     بشپ
    0.08
     canvi
    0.08
    കള
    0.08
    Act Density 0.003%

    No Known Activations