INDEX
Explanations
indicators of article publication and update timestamps
New Auto-Interp
Negative Logits
hawks
-0.17
hani
-0.17
oso
-0.16
uldu
-0.16
ijken
-0.15
ombat
-0.14
erton
-0.14
dra
-0.14
TRGL
-0.14
entry
-0.14
POSITIVE LOGITS
Citizen
0.15
rib
0.14
вод
0.14
Cous
0.14
Hell
0.14
ype
0.14
Smarty
0.14
_superuser
0.14
ima
0.14
taskId
0.13
Activations Density 0.005%