INDEX
    Explanations

    references to familial relationships, specifically brothers and sisters

    New Auto-Interp
    Negative Logits
    UserScript
    -0.87
     незавершена
    -0.82
     CURIAM
    -0.80
    JpaRepository
    -0.77
     שוליים
    -0.76
    AccessorTable
    -0.76
    InstanceState
    -0.75
    Sucesor
    -0.74
     ujednoznacz
    -0.74
    Personendaten
    -0.73
    POSITIVE LOGITS
     Brothers
    1.19
    Brothers
    1.16
     BROTHERS
    1.04
     Sisters
    1.03
     brothers
    0.95
    Sisters
    0.90
     sisters
    0.86
    brothers
    0.77
     Brüder
    0.68
     Bros
    0.67
    Act Density 0.112%

    No Known Activations