INDEX
    Explanations

    references to Hispanic and Latino identities or communities

    New Auto-Interp
    Negative Logits
    nee
    -0.16
     Ñģм
    -0.15
    nger
    -0.15
    .son
    -0.15
     fork
    -0.14
    аÑĢÑĩ
    -0.14
    Sense
    -0.14
    ->{_
    -0.14
    unned
    -0.13
     Wort
    -0.13
    POSITIVE LOGITS
    670
    0.16
    ugal
    0.15
    _attrib
    0.15
    ضر
    0.14
    452
    0.14
    .contents
    0.14
    paces
    0.14
    736
    0.14
    ools
    0.14
    -Muslim
    0.14
    Act Density 0.010%

    No Known Activations