INDEX
Explanations
references to love and relationships, especially in the context of commitment and gifts
New Auto-Interp
Negative Logits
inoa
-0.07
ceph
-0.07
hiro
-0.07
imbus
-0.07
upported
-0.06
atown
-0.06
puter
-0.06
egra
-0.06
urator
-0.06
nova
-0.06
POSITIVE LOGITS
couples
0.12
romantic
0.12
romance
0.11
Couples
0.11
Romantic
0.11
love
0.10
Romeo
0.10
couple
0.10
Couple
0.10
Romance
0.09
Activations Density 0.061%