INDEX
Explanations
proper nouns related to politics and individuals
references to specific individuals, particularly those named "Mam" and "Mikhail."
New Auto-Interp
Negative Logits
kson
-0.77
¯¯¯¯
-0.75
ä½ľ
-0.73
Minecraft
-0.68
Falk
-0.63
backer
-0.62
trough
-0.60
ying
-0.60
Drug
-0.60
Syd
-0.60
POSITIVE LOGITS
Mam
0.87
amia
0.84
onde
0.83
ueller
0.80
aj
0.80
umin
0.80
lu
0.79
aret
0.78
noon
0.76
oufl
0.74
Activations Density 0.016%