INDEX
    Explanations

    sexual abuse

    New Auto-Interp
    Negative Logits
     unsecured
    -0.08
     Ablauf
    -0.08
     accreditation
    -0.07
     pert
    -0.07
     lunch
    -0.07
     She
    -0.07
     rump
    -0.07
     دل
    -0.07
     bew
    -0.07
     dele
    -0.07
    POSITIVE LOGITS
     perro
    0.09
     ascol
    0.08
     lugar
    0.08
    0.08
     อย
    0.08
     ਨਾ
    0.08
     venant
    0.08
     chant
    0.08
     moedas
    0.08
     ó
    0.08
    Act Density 0.004%

    No Known Activations