INDEX
Explanations
gerunds, present participles, or verbs indicating action and strong emotional or sensory experiences
New Auto-Interp
Negative Logits
yro
-0.16
810
-0.16
ataka
-0.15
OLA
-0.14
airo
-0.14
Kear
-0.14
éłĵ
-0.13
sale
-0.13
paque
-0.13
ecta
-0.13
POSITIVE LOGITS
Burk
0.15
Merk
0.15
Meyer
0.15
Mess
0.15
ura
0.15
loh
0.14
.TODO
0.14
levant
0.14
à¸Ĺะ
0.13
orry
0.13
Activations Density 0.009%