INDEX
Explanations
references to the political situation in Rwanda
New Auto-Interp
Negative Logits
Liver
-0.17
Saudi
-0.16
ä½
-0.16
Kapoor
-0.16
ffc
-0.16
Liver
-0.16
Saudi
-0.15
thai
-0.15
apel
-0.15
assel
-0.15
POSITIVE LOGITS
Rwanda
0.45
Rw
0.43
rw
0.33
Hut
0.32
rw
0.31
genocide
0.29
Kag
0.29
RW
0.28
RW
0.28
Ny
0.26
Activations Density 0.030%