INDEX
Explanations
references to vaccines and vaccination-related discussions
New Auto-Interp
Negative Logits
reinc
-0.16
sess
-0.14
æ·
-0.14
odus
-0.14
PCA
-0.14
201
-0.13
åĬŀçIJĨ
-0.13
avers
-0.13
ivor
-0.13
оди
-0.13
POSITIVE LOGITS
vaccine
0.27
mRNA
0.25
Cov
0.24
vaccines
0.23
Warp
0.23
vacc
0.22
jab
0.22
doses
0.22
вак
0.22
Vaccine
0.22
Activations Density 0.036%