INDEX
Explanations
references to events, locations, and dates
New Auto-Interp
Negative Logits
Lanka
-0.17
ongan
-0.15
کارÛĮ
-0.15
lament
-0.15
uki
-0.15
ocode
-0.14
uin
-0.14
uyu
-0.14
Barcl
-0.14
arkan
-0.14
POSITIVE LOGITS
Split
0.27
Nice
0.26
Tall
0.26
Graz
0.23
Tur
0.23
Gen
0.22
Tours
0.22
Gent
0.21
Zar
0.21
Trom
0.21
Activations Density 0.212%