INDEX
    Explanations

    mentions of specific locations or countries

    New Auto-Interp
    Negative Logits
    owie
    -0.19
    _Tis
    -0.16
    ois
    -0.16
    ères
    -0.16
    otti
    -0.15
    adro
    -0.14
    ÌĨ
    -0.14
    हर
    -0.14
    DialogTitle
    -0.14
    resse
    -0.14
    POSITIVE LOGITS
     Howe
    0.15
    ZONE
    0.14
    ny
    0.14
     Dun
    0.14
     ours
    0.14
     ún
    0.13
     ones
    0.13
     Blick
    0.13
    885
    0.13
    chief
    0.13
    Act Density 0.134%

    No Known Activations