INDEX
    Explanations

    references to individuals and their relationships with others, often highlighting their roles within a family or social context

    New Auto-Interp
    Negative Logits
     husbands
    -0.93
    MessageTagHelper
    -0.92
     male
    -0.89
    Male
    -0.87
     متعلقه
    -0.86
     males
    -0.85
    Personendaten
    -0.82
     Male
    -0.82
     mascul
    -0.79
     männ
    -0.78
    POSITIVE LOGITS
     widow
    0.64
     sorcer
    0.62
     wife
    0.61
     propriet
    0.55
     mother
    0.52
     beautiful
    0.51
     enchant
    0.51
     Propriet
    0.51
     stepmother
    0.49
     bellissima
    0.49
    Act Density 0.285%

    No Known Activations