INDEX
    Explanations

    references to legislative and governmental bodies

    New Auto-Interp
    Negative Logits
    getResponse
    -0.15
    resden
    -0.14
    ROOT
    -0.14
    ibre
    -0.14
    Ñĵ
    -0.14
    ÑİÑĢ
    -0.14
    ington
    -0.13
    indow
    -0.13
    AKE
    -0.13
    kate
    -0.13
    POSITIVE LOGITS
    arians
    0.21
    arian
    0.18
    ional
    0.17
    ion
    0.16
    ships
    0.15
    /media
    0.15
     Commons
    0.15
    à¥Ģय
    0.15
    reesome
    0.15
    iris
    0.15
    Act Density 0.041%

    No Known Activations