INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    -0.09
     berupa
    -0.09
     Biz
    -0.08
    -0.08
    -0.08
     Supplemental
    -0.08
     Restr
    -0.07
     Eind
    -0.07
     Frag
    -0.07
     pomoc
    -0.07
    POSITIVE LOGITS
     autoestima
    0.15
    Self
    0.11
     Self
    0.11
    _self
    0.11
     আত্ম
    0.10
     self
    0.10
     자신
    0.10
     narciss
    0.10
     নিজের
    0.10
     आत्म
    0.10
    Act Density 0.028%

    No Known Activations