INDEX
Explanations
expressions related to physical sensations and personal experiences
New Auto-Interp
Negative Logits
SizeMode
-0.14
Stevenson
-0.14
atisfied
-0.14
Morris
-0.14
yor
-0.14
Commonwealth
-0.13
chez
-0.13
Boot
-0.13
circumstance
-0.13
blind
-0.13
POSITIVE LOGITS
nite
0.16
è͵
0.16
ÙĦÛĮس
0.15
kola
0.15
Burst
0.14
ocz
0.14
OTES
0.14
agal
0.14
eos
0.14
Insider
0.14
Activations Density 0.195%