INDEX
    Explanations

    mentions of COVID-19 and its associated impacts

    New Auto-Interp
    Negative Logits
    ojÃŃ
    -0.15
    IDADE
    -0.15
    ahy
    -0.14
    sko
    -0.14
    IBE
    -0.14
    quil
    -0.14
    بÙĪØ¯
    -0.14
     Zum
    -0.13
    æ°¸ä¹ħ
    -0.13
    ainter
    -0.13
    POSITIVE LOGITS
    yw
    0.17
     Macy
    0.15
    Ñİдж
    0.15
    apesh
    0.14
    akit
    0.14
     hitch
    0.14
    _INITIALIZ
    0.14
     ward
    0.14
     fought
    0.14
    30
    0.13
    Act Density 0.019%

    No Known Activations