INDEX
Explanations
institutions and universities
New Auto-Interp
Negative Logits
burger
-0.17
OMET
-0.15
adem
-0.15
ewe
-0.15
chy
-0.14
enu
-0.14
Ref
-0.14
registered
-0.14
ivor
-0.14
538
-0.14
POSITIVE LOGITS
fold
0.16
coma
0.16
Fraser
0.15
Schwartz
0.15
CEE
0.14
ifar
0.14
Wit
0.14
shaw
0.14
ochen
0.14
ystone
0.14
Activations Density 0.027%