INDEX
Explanations
mention of vaccination or related health topics
New Auto-Interp
Negative Logits
Dimension
-0.14
Ders
-0.14
.Networking
-0.14
grap
-0.14
L
-0.14
Touch
-0.13
zar
-0.13
#ad
-0.13
stellen
-0.13
vä
-0.13
POSITIVE LOGITS
844
0.17
reporter
0.17
McCl
0.17
reporters
0.17
icaid
0.15
Kaiser
0.15
watchdog
0.15
Reporting
0.15
tracker
0.15
reporting
0.15
Activations Density 0.159%