INDEX
Explanations
mentions of COVID-19 and associated vaccinations in various contexts
New Auto-Interp
Negative Logits
iami
-0.20
zug
-0.16
ired
-0.15
ora
-0.14
hrad
-0.14
krét
-0.14
PIP
-0.14
MEA
-0.14
loe
-0.14
errated
-0.14
POSITIVE LOGITS
iem
0.16
ikit
0.14
gio
0.14
trop
0.14
Es
0.14
alim
0.14
erot
0.14
hem
0.14
conven
0.13
cro
0.13
Activations Density 0.123%