INDEX
Explanations
divine or majestic qualities and characteristics
pronouns and possessive forms in text
New Auto-Interp
Negative Logits
Jam
-0.75
ipers
-0.67
IDs
-0.65
Manip
-0.64
ISON
-0.63
Lines
-0.63
Lock
-0.61
hack
-0.61
imates
-0.60
abwe
-0.60
POSITIVE LOGITS
elf
0.91
theless
0.71
fate
0.69
disposition
0.67
psey
0.67
antle
0.67
usual
0.66
mood
0.66
owship
0.62
destiny
0.62
Activations Density 0.303%