INDEX
Explanations
terms and phrases related to cognition, awareness, and mental states
New Auto-Interp
Negative Logits
antino
-0.20
pekt
-0.17
izzly
-0.17
mana
-0.16
asio
-0.15
uada
-0.15
essian
-0.15
otos
-0.15
stype
-0.15
iser
-0.14
POSITIVE LOGITS
lessly
0.21
cape
0.16
fulness
0.16
rap
0.16
fully
0.16
/body
0.15
sets
0.15
837
0.15
less
0.15
ning
0.14
Activations Density 0.053%