INDEX
Explanations
references to colonial powers and their influence over territories
New Auto-Interp
Negative Logits
associ
-0.16
528
-0.15
ooky
-0.15
itudes
-0.14
139
-0.14
associate
-0.13
çĢ
-0.13
associate
-0.13
ika
-0.13
iggs
-0.13
POSITIVE LOGITS
QR
0.15
cies
0.15
bart
0.14
RunLoop
0.14
uart
0.14
-desc
0.14
/Main
0.14
flush
0.14
orf
0.13
nels
0.13
Activations Density 0.051%