INDEX
Explanations
attends to definitions or explanatory phrases from the context of political events or terminology
New Auto-Interp
Head Attr Weights
0:0.07
1:0.09
2:0.08
3:0.09
4:0.08
5:0.03
6:0.36
7:0.16
Negative Logits
-0.34
saites
-0.30
بتاريخ
-0.30
)");
-0.30
RegressionTest
-0.29
;">
-0.28
urally
-0.28
SharedDtor
-0.28
مرئيه
-0.27
\
-0.27
POSITIVE LOGITS
sumpay
0.38
tableFuture
0.35
địch
0.33
prisonniers
0.33
المعيارى
0.33
delantera
0.33
ước
0.32
BrowserModule
0.32
ToScroll
0.32
étit
0.31
Activations Density 0.064%