INDEX
Explanations
references to political and economic integration within Europe
New Auto-Interp
Negative Logits
esen
-0.17
Job
-0.17
jee
-0.16
job
-0.16
woff
-0.15
eson
-0.15
_TUN
-0.15
jo
-0.15
Dou
-0.15
dz
-0.15
POSITIVE LOGITS
arcy
0.16
ASI
0.15
Monetary
0.15
Spor
0.15
ire
0.14
umm
0.14
åį¡
0.14
ktop
0.14
HS
0.13
redefine
0.13
Activations Density 0.025%