INDEX
Explanations
terms related to health and safety measures, particularly those associated with social distancing and protective equipment
New Auto-Interp
Negative Logits
à¹Īà¸Ńà¸Ļ
-0.15
timeofday
-0.15
ooth
-0.15
icked
-0.14
wys
-0.14
Podesta
-0.14
kiye
-0.14
رز
-0.13
ighth
-0.13
گاÙĩ
-0.13
POSITIVE LOGITS
oler
0.17
inea
0.14
plier
0.14
ozÃŃ
0.14
iji
0.14
RTC
0.13
Journalism
0.13
nez
0.13
.messages
0.13
Hack
0.13
Activations Density 0.025%