INDEX
Explanations
mentions of specific political figures, particularly Silvio Berlusconi
proper nouns and names related to specific entities or locations
New Auto-Interp
Negative Logits
reconc
-0.73
eering
-0.72
replication
-0.71
¥ŀ
-0.68
anked
-0.65
journal
-0.65
warranties
-0.65
ribbon
-0.64
testament
-0.64
replicate
-0.64
POSITIVE LOGITS
lus
1.17
colo
1.03
HUD
1.01
coni
0.93
cious
0.90
cano
0.89
hement
0.89
cone
0.89
phia
0.86
gro
0.86
Activations Density 0.008%