INDEX
Explanations
expressions of certainty or judgment
New Auto-Interp
Negative Logits
èŀ
-0.14
ein
-0.14
èo
-0.14
ép
-0.13
aney
-0.13
MBOL
-0.13
-alist
-0.13
454
-0.13
383
-0.13
_hop
-0.13
POSITIVE LOGITS
odef
0.16
wn
0.15
chine
0.15
èĩ
0.14
duy
0.14
Cert
0.13
otland
0.13
uhe
0.13
.pt
0.13
[*
0.12
Activations Density 0.000%