INDEX
Explanations
mentions of educational institutions and geographic locations in Texas
New Auto-Interp
Negative Logits
جد
-0.16
undra
-0.16
Nad
-0.15
trand
-0.15
empor
-0.14
phyl
-0.14
udded
-0.14
apollo
-0.14
acier
-0.14
afen
-0.14
POSITIVE LOGITS
UT
0.19
UT
0.19
Arlington
0.19
ut
0.17
Perm
0.17
Perm
0.16
774
0.16
ut
0.15
utex
0.15
Ariel
0.15
Activations Density 0.006%