INDEX
    Explanations

    references to the coronavirus and related public health measures

    New Auto-Interp
    Negative Logits
    олж
    -0.16
    ruž
    -0.16
    isle
    -0.15
     Skin
    -0.15
    RAIN
    -0.15
    innie
    -0.15
     Gilles
    -0.14
     Göz
    -0.14
    culate
    -0.14
     vandal
    -0.14
    POSITIVE LOGITS
     Variant
    0.17
    appen
    0.16
    Ñĥже
    0.15
    apesh
    0.15
     ê²
    0.15
     Transmission
    0.15
    áš
    0.15
    uger
    0.15
    ugu
    0.14
    ä¼Ŀ
    0.14
    Act Density 0.040%

    No Known Activations