INDEX
Explanations
words and phrases related to kissing and romance
New Auto-Interp
Negative Logits
hurst
-0.15
493
-0.15
hap
-0.15
zag
-0.15
unto
-0.15
ught
-0.15
hift
-0.15
bens
-0.14
zman
-0.14
ifference
-0.14
POSITIVE LOGITS
Kiss
0.30
kiss
0.28
goodbye
0.26
kissed
0.20
(es
0.20
lips
0.20
Lip
0.19
Lips
0.19
kissing
0.19
lip
0.18
Activations Density 0.011%