INDEX
Explanations
references to years and numerical data
New Auto-Interp
Negative Logits
rica
-0.18
_tick
-0.17
SOC
-0.16
_KHR
-0.16
imper
-0.15
é£İ
-0.15
Ñĥгод
-0.15
ÙĨب
-0.14
sez
-0.14
prive
-0.14
POSITIVE LOGITS
inger
0.19
emos
0.17
ÑĢан
0.15
-La
0.15
onn
0.15
лаз
0.15
Bryan
0.15
Mess
0.14
Hess
0.14
ini
0.14
Activations Density 0.037%