INDEX
    Explanations

    references to racial and ethnic identity and discussions around inclusivity and experiences of marginalized groups

    New Auto-Interp
    Negative Logits
     Zusammen
    -0.53
     someone
    -0.47
    namientos
    -0.47
     itself
    -0.45
     Itself
    -0.45
    someone
    -0.45
     estando
    -0.43
     alguém
    -0.42
     somebody
    -0.42
    somebody
    -0.41
    POSITIVE LOGITS
     whom
    0.60
    CloseOperation
    0.59
     backgrounds
    0.53
    ंदीखरीदारी
    0.53
    WithIOException
    0.51
     academia
    0.51
    whom
    0.51
     wheelchairs
    0.48
     faiths
    0.47
    featureID
    0.46
    Act Density 0.533%

    No Known Activations