INDEX
Explanations
expressions of personal feelings or states of being
New Auto-Interp
Negative Logits
lector
-0.17
úng
-0.15
aterno
-0.15
itself
-0.15
airo
-0.14
$MESS
-0.14
å¹
-0.14
bilt
-0.14
ngrx
-0.14
ÐľÑĸ
-0.14
POSITIVE LOGITS
tec
0.18
sorry
0.16
sure
0.16
allet
0.16
currently
0.15
aze
0.15
sim
0.15
Sure
0.15
erson
0.14
men
0.14
Activations Density 0.094%