INDEX
    Explanations

    words related to demographics, particularly race and ethnicity

    New Auto-Interp
    Negative Logits
     branche
    -0.47
     Grote
    -0.46
     el
    -0.46
    Personensuche
    -0.45
     paroi
    -0.45
     privilégi
    -0.44
    borg
    -0.43
     espirituales
    -0.42
     interface
    -0.42
     doigt
    -0.42
    POSITIVE LOGITS
    MockBean
    0.87
    AddTagHelper
    0.80
    InjectMocks
    0.65
    ViewImports
    0.63
     intptr
    0.63
    TagHelpers
    0.59
    ViewFeatures
    0.58
    issage
    0.57
    twimg
    0.57
     nô
    0.56
    Act Density 17.533%

    No Known Activations