INDEX
Explanations
mentions of specific individuals' names
New Auto-Interp
Negative Logits
ysa
-0.15
egt
-0.15
Gross
-0.15
ubar
-0.15
.googleapis
-0.14
ioc
-0.14
tero
-0.14
adar
-0.14
PostBack
-0.14
empor
-0.14
POSITIVE LOGITS
arg
0.18
AGES
0.15
thr
0.15
inet
0.15
Towers
0.14
prob
0.14
UIT
0.13
nici
0.13
elman
0.13
Dort
0.13
Activations Density 0.043%