INDEX
Explanations
significant mentions of America and related cultural discussions
New Auto-Interp
Negative Logits
avez
-0.16
cone
-0.15
_mt
-0.14
åĿ
-0.14
rip
-0.14
åŃĹ
-0.14
ockey
-0.13
rak
-0.13
ephy
-0.13
pee
-0.13
POSITIVE LOGITS
mdi
0.16
ensch
0.16
---------------------------------------------------------------------------↵
0.15
Tru
0.15
benzer
0.15
é¾Ħ
0.14
ialized
0.14
ageing
0.14
_sys
0.14
lider
0.14
Activations Density 0.009%