INDEX
Explanations
information related to health and safety protocols, particularly regarding COVID-19 cases and government responses
New Auto-Interp
Negative Logits
upert
-0.16
ause
-0.15
aban
-0.14
southeastern
-0.14
erman
-0.14
affer
-0.14
assing
-0.14
colors
-0.14
antee
-0.14
214
-0.13
POSITIVE LOGITS
.onView
0.18
.setAuto
0.15
Seks
0.14
EMON
0.13
Zur
0.13
ìķĻ
0.13
wholesome
0.13
hrom
0.13
Äįan
0.13
relevant
0.13
Activations Density 0.011%