INDEX
Explanations
words related to political figures and their actions
words related to aging and age-related themes
New Auto-Interp
Negative Logits
ocument
-0.82
ntil
-0.77
geoning
-0.69
atural
-0.66
ancial
-0.65
iaries
-0.65
usterity
-0.64
olicy
-0.64
rupulous
-0.63
acters
-0.63
POSITIVE LOGITS
ault
0.90
llan
0.88
ño
0.87
witz
0.87
Pearce
0.83
y
0.82
mont
0.80
Schmidt
0.78
Gardner
0.78
hart
0.78
Activations Density 0.129%