INDEX
    Explanations

    geographical features

    New Auto-Interp
    Negative Logits
     bf
    -0.06
    btn
    -0.06
     neboť
    -0.06
    correo
    -0.06
     backpage
    -0.06
    incr
    -0.06
     Fet
    -0.06
     perfume
    -0.06
     vej
    -0.06
    Hop
    -0.06
    POSITIVE LOGITS
    ocratic
    0.08
     excess
    0.07
     Command
    0.07
    uable
    0.07
     pencil
    0.06
    IFEST
    0.06
     waters
    0.06
    asuring
    0.06
     dateFormat
    0.06
    ILES
    0.06
    Act Density 0.028%

    No Known Activations