INDEX
    Explanations

    mentions of medical conditions and related terminology

    New Auto-Interp
    Negative Logits
     כ
    -1.55
     הכ
    -0.62
    כ
    -0.58
     וכ
    -0.51
     בכ
    -0.48
    minecraftforge
    -0.41
    mtrl
    -0.41
     כח
    -0.40
     πο
    -0.40
    unc
    -0.39
    POSITIVE LOGITS
    featureID
    0.54
    rungsseite
    0.52
     resourceCulture
    0.52
    tvguidetime
    0.52
    numerusform
    0.52
     Италијани
    0.50
    ########.
    0.50
     فريبيس
    0.48
     Jefus
    0.47
     againſt
    0.45
    Act Density 0.000%

    No Known Activations