INDEX
    Explanations

    "to be" forms

    New Auto-Interp
    Negative Logits
     purchasing
    -0.07
     kuk
    -0.06
    POS
    -0.06
     divisor
    -0.06
     seated
    -0.06
     mentions
    -0.06
     قب
    -0.06
    itched
    -0.06
     هن
    -0.06
    Cab
    -0.06
    POSITIVE LOGITS
    0.08
    ofday
    0.08
    _Two
    0.07
     inflamm
    0.06
     sân
    0.06
    Foreground
    0.06
    _da
    0.06
    iolet
    0.06
    onDelete
    0.06
    amm
    0.06
    Act Density 0.009%

    No Known Activations