INDEX
Explanations
references to the European Union and its institutions
New Auto-Interp
Negative Logits
uner
-0.17
ierce
-0.15
Toast
-0.15
anne
-0.15
stan
-0.15
European
-0.14
nn
-0.14
æŃIJ
-0.14
Feinstein
-0.14
Europe
-0.14
POSITIVE LOGITS
Union
0.34
Union
0.30
UNION
0.29
union
0.28
union
0.28
_union
0.24
Commission
0.23
.union
0.20
ization
0.19
isation
0.18
Activations Density 0.015%