INDEX
    Explanations

    references to gender pronouns

    New Auto-Interp
    Negative Logits
     Baillargeon
    -0.79
    adaptiveStyles
    -0.71
     AssemblyCulture
    -0.71
    IntoConstraints
    -0.63
     Extragalactic
    -0.62
    MessageState
    -0.61
     चीज़ों
    -0.61
    HideFlags
    -0.60
     Donat
    -0.59
    DockStyle
    -0.58
    POSITIVE LOGITS
     person
    0.64
    person
    0.62
    óság
    0.58
    سجيل
    0.55
    herself
    0.54
     Dafür
    0.53
    BeginContext
    0.52
    REQUIRES
    0.51
     sexe
    0.51
    0.51
    Act Density 0.059%

    No Known Activations