INDEX
Explanations
references to dates and time periods
New Auto-Interp
Negative Logits
jni
-0.17
xit
-0.16
èŀ
-0.15
æŀĹ
-0.15
och
-0.15
Protest
-0.14
licken
-0.14
862
-0.14
æĻ¨
-0.14
etter
-0.14
POSITIVE LOGITS
conte
0.16
agon
0.14
.bulk
0.14
iates
0.14
_bulk
0.14
ajas
0.13
court
0.13
gerçekleÅŁtir
0.13
θε
0.13
held
0.13
Activations Density 0.128%