INDEX
Explanations
references to breaks and time off from work
New Auto-Interp
Negative Logits
iales
-0.19
bourg
-0.17
lei
-0.16
udge
-0.16
ToLocal
-0.15
rescia
-0.15
245
-0.15
intptr
-0.14
osu
-0.14
ÙģØ§Øª
-0.14
POSITIVE LOGITS
olini
0.18
uras
0.17
tha
0.16
Tomáš
0.16
ÙĨص
0.15
sexes
0.14
ZH
0.14
Mur
0.14
Tou
0.14
ZE
0.14
Activations Density 0.085%