INDEX
Explanations
contexts related to emotional or physical sensations
New Auto-Interp
Negative Logits
TestBed
-0.56
Educ
-0.53
initWithFrame
-0.52
">+
-0.49
lior
-0.48
astre
-0.48
favicon
-0.47
<?
-0.47
ERTE
-0.46
Kid
-0.46
POSITIVE LOGITS
whisper
1.36
whispered
1.30
whispering
1.29
whispers
1.24
murmurs
1.23
murmured
1.22
murmuring
1.21
murmur
1.20
muttering
1.17
whisper
1.16
Activations Density 0.352%