INDEX
Explanations
verbs related to acquiring or obtaining
New Auto-Interp
Negative Logits
804
-0.16
480
-0.15
Score
-0.14
OLL
-0.14
aco
-0.14
iger
-0.14
ospace
-0.14
.keyword
-0.13
Detail
-0.13
arium
-0.13
POSITIVE LOGITS
round
0.27
stuck
0.22
round
0.21
stick
0.20
ROUND
0.19
Round
0.18
-round
0.18
Stick
0.17
Stick
0.17
Round
0.17
Activations Density 0.047%