INDEX
    Explanations

    references to geographical locations and political entities, particularly in relation to Africa

    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -1.00
     myſelf
    -0.80
     Jefus
    -0.80
     Monfieur
    -0.78
     Theſe
    -0.78
     itſelf
    -0.75
     Мексичка
    -0.75
     uſed
    -0.72
     espagnole
    -0.69
     beginnetje
    -0.69
    POSITIVE LOGITS
    lawayo
    0.75
     Zimbabwe
    0.69
     Harare
    0.68
    Zimbabwe
    0.67
     Mugabe
    0.66
    babwe
    0.62
     Malawi
    0.57
    wira
    0.54
    ModelForm
    0.54
     zve
    0.52
    Act Density 0.201%

    No Known Activations