INDEX
Explanations
references to Scotland and its governing bodies
New Auto-Interp
Negative Logits
ulia
-0.15
rias
-0.15
esine
-0.14
UDA
-0.14
Russo
-0.14
.slim
-0.14
OTAL
-0.14
Trib
-0.13
kus
-0.13
ithe
-0.13
POSITIVE LOGITS
ifi
0.16
ÄĮech
0.16
andi
0.15
sdale
0.15
Huck
0.15
osy
0.15
paces
0.14
agnost
0.14
asar
0.14
abra
0.14
Activations Density 0.005%