INDEX
Explanations
elements related to local news reporting and community health issues
New Auto-Interp
Negative Logits
eras
-0.16
orra
-0.15
ALSE
-0.15
иж
-0.14
rej
-0.14
pired
-0.14
аÑħ
-0.14
657
-0.14
iz
-0.14
ihat
-0.14
POSITIVE LOGITS
Sag
0.15
Den
0.14
adeon
0.13
še
0.13
ometr
0.13
allen
0.13
scor
0.13
tep
0.13
masc
0.13
scp
0.13
Activations Density 0.013%