INDEX
    Explanations

    references to reproductive health and pregnancy-related conditions

    New Auto-Interp
    Negative Logits
     businesswoman
    -0.92
     herself
    -0.92
    herself
    -0.88
     actress
    -0.87
     actresses
    -0.84
     goddess
    -0.81
     Baroness
    -0.80
     Kaur
    -0.79
     Autorin
    -0.76
     heroine
    -0.76
    POSITIVE LOGITS
     pria
    1.06
     masculinity
    1.06
     manhood
    1.00
     male
    1.00
     gentlemen
    0.99
     gentleman
    0.99
     manly
    0.99
     mężczy
    0.96
     Gentleman
    0.96
     father
    0.96
    Act Density 0.607%

    No Known Activations