INDEX
Explanations
references to specific decades, particularly the 60s and 70s
New Auto-Interp
Negative Logits
ter
-0.16
v
-0.16
amar
-0.15
Ju
-0.14
inf
-0.14
chn
-0.14
access
-0.14
etro
-0.14
AM
-0.14
values
-0.14
POSITIVE LOGITS
arsers
0.16
.gdx
0.16
ienes
0.16
olist
0.15
Ñħа
0.15
oton
0.15
ÃŃda
0.15
обов
0.14
ori
0.14
$MESS
0.14
Activations Density 0.026%