INDEX
Explanations
descriptors of enjoyable experiences related to various forms of entertainment and consumer products
New Auto-Interp
Negative Logits
ivr
-0.15
rita
-0.14
AME
-0.14
itmap
-0.14
:checked
-0.14
Wik
-0.14
ante
-0.14
Wiki
-0.14
uges
-0.14
olum
-0.14
POSITIVE LOGITS
discern
0.21
discrim
0.20
serious
0.19
fans
0.19
die
0.19
ÑĨен
0.18
anyone
0.18
arm
0.17
lovers
0.17
advanced
0.17
Activations Density 0.145%