INDEX
Explanations
names and surnames from a specific cultural or linguistic context
New Auto-Interp
Negative Logits
ège
-0.15
alion
-0.14
kans
-0.14
丰
-0.14
eteria
-0.14
Wein
-0.14
tery
-0.14
poor
-0.14
-way
-0.14
Way
-0.14
POSITIVE LOGITS
unw
0.15
brero
0.15
ãĥ¼ãĥ«
0.14
Pod
0.14
Painter
0.14
iloc
0.14
bial
0.13
itals
0.13
Nation
0.13
ustralian
0.13
Activations Density 0.022%