INDEX
Explanations
proper names related to political figures
names of prominent individuals or political leaders
New Auto-Interp
Negative Logits
LEASE
-0.67
FANTASY
-0.66
66666666
-0.62
sburgh
-0.61
rica
-0.61
Pokemon
-0.60
Aliens
-0.59
hetical
-0.58
rius
-0.58
VIDE
-0.58
POSITIVE LOGITS
hart
0.90
arde
0.78
otti
0.77
ovich
0.77
zynski
0.77
iani
0.73
bard
0.73
zinski
0.73
insky
0.73
owitz
0.72
Activations Density 0.202%