INDEX
    Explanations

    references to characters involved in crime or conflict situations

    New Auto-Interp
    Negative Logits
    Äįel
    -0.17
    offsetof
    -0.17
    ibold
    -0.16
    celik
    -0.16
    porno
    -0.16
    abar
    -0.15
    Porno
    -0.15
    .synthetic
    -0.15
    Intialized
    -0.15
    oload
    -0.14
    POSITIVE LOGITS
     
    0.16
    iegel
    0.14
    i
    0.14
    ãģĸ
    0.14
    024
    0.14
     Aval
    0.13
     Pav
    0.13
     Pend
    0.13
     Criterion
    0.13
     Gym
    0.13
    Act Density 0.053%

    No Known Activations