INDEX
Explanations
words related to romantic relationships
mentions of romance and romantic themes
New Auto-Interp
Negative Logits
umbnail
-0.80
affer
-0.77
individual
-0.69
aepernick
-0.66
omin
-0.64
aton
-0.64
osta
-0.64
eret
-0.63
ividual
-0.63
ulk
-0.61
POSITIVE LOGITS
romance
0.93
uality
0.81
Romance
0.80
novelist
0.76
ogue
0.76
Royale
0.72
nexus
0.72
novels
0.71
banter
0.66
Frankenstein
0.64
Activations Density 0.009%