INDEX
Explanations
mentions of heartfelt emotions or sentiments
references to "hearts" or expressions of emotional depth and feeling
New Auto-Interp
Negative Logits
utory
-0.69
urer
-0.65
Codec
-0.63
ı
-0.63
supplement
-0.62
rete
-0.62
author
-0.62
sche
-0.61
Der
-0.61
pesticide
-0.60
POSITIVE LOGITS
hearts
4.26
minds
2.01
Hearts
1.95
souls
1.89
heart
1.78
necks
1.64
throats
1.60
chests
1.48
skulls
1.41
ears
1.37
Activations Density 0.018%