INDEX
Explanations
elements of romantic relationships and personal stories regarding love and marriage
New Auto-Interp
Negative Logits
ISCO
-0.16
ãĤ¢ãĥ«ãĥIJ
-0.15
ubb
-0.14
alph
-0.14
nard
-0.14
kyt
-0.14
mascot
-0.13
mrb
-0.13
ERCHANT
-0.13
Lover
-0.13
POSITIVE LOGITS
model
0.19
estr
0.18
model
0.18
actor
0.17
-model
0.17
/model
0.16
req
0.15
actor
0.15
actress
0.15
whom
0.14
Activations Density 0.069%