INDEX
    Explanations

    Christianity

    New Auto-Interp
    Negative Logits
     цар
    -0.07
    .patch
    -0.07
     LABEL
    -0.06
     уж
    -0.06
    ава
    -0.06
     BANK
    -0.06
     поч
    -0.06
    ştır
    -0.06
     sel
    -0.06
    .Len
    -0.06
    POSITIVE LOGITS
    овала
    0.07
    овали
    0.07
    овал
    0.07
    0.07
    ансов
    0.06
    atisfied
    0.06
    onents
    0.06
    ็็
    0.06
    0.06
    Illegal
    0.06
    Act Density 0.026%

    No Known Activations