INDEX
Explanations
phrases expressing beauty, admiration, and subjective opinions about people and experiences
New Auto-Interp
Negative Logits
ÑĮми
-0.17
acom
-0.15
ypi
-0.15
ernen
-0.14
opis
-0.14
953
-0.14
303
-0.14
abis
-0.14
zel
-0.14
430
-0.13
POSITIVE LOGITS
.setAuto
0.15
аÑĢан
0.14
contrib
0.14
viol
0.14
Tyson
0.13
Settlement
0.13
Ty
0.13
ward
0.13
ardin
0.13
ny
0.13
Activations Density 0.319%