INDEX
Negative Logits
=-
0.45
haunting
0.42
frightening
0.42
conical
0.41
terrifying
0.40
frust
0.40
悲
0.40
⇌
0.38
=-\
0.38
픔
0.38
POSITIVE LOGITS
praise
2.98
praising
2.75
praises
2.58
Praise
2.52
प्रशंसा
2.42
praised
2.39
compliment
2.33
প্রশংসা
2.30
compliments
2.27
तारीफ
2.17
Activations Density 0.088%