INDEX
Explanations
mentions of Sudan and its people
New Auto-Interp
Negative Logits
igli
-0.15
ugar
-0.15
yll
-0.14
ex
-0.14
Preis
-0.14
arro
-0.14
éļĶ
-0.14
cke
-0.14
hoa
-0.13
usc
-0.13
POSITIVE LOGITS
kowski
0.19
Loss
0.15
edn
0.15
-FIRST
0.15
eld
0.15
оÑİ
0.15
insky
0.15
utzer
0.14
loss
0.14
ÚĨÙĩ
0.14
Activations Density 0.005%