INDEX
Explanations
descriptors and actions related to personal experiences and interactions with nature
New Auto-Interp
Negative Logits
elson
-0.16
ael
-0.15
ister
-0.15
anut
-0.15
anik
-0.15
ants
-0.14
igg
-0.14
umin
-0.14
jang
-0.14
Kramer
-0.14
POSITIVE LOGITS
NOP
0.14
ienes
0.14
haf
0.14
Amend
0.14
letic
0.14
exter
0.14
Lauderdale
0.14
vert
0.14
ctl
0.13
Escort
0.13
Activations Density 3.110%