INDEX
Explanations
proper names, particularly those of individuals associated with academic or professional achievements
New Auto-Interp
Negative Logits
Fel
-0.15
Stencil
-0.15
Fel
-0.14
arian
-0.14
tua
-0.14
oles
-0.13
preload
-0.13
elman
-0.13
mach
-0.13
istar
-0.13
POSITIVE LOGITS
avra
0.16
utz
0.15
廳
0.15
cope
0.14
359
0.14
Sims
0.14
วà¸ģ
0.14
idge
0.14
merce
0.14
orne
0.14
Activations Density 0.161%