INDEX
Explanations
names of individuals, particularly in a historical or biographical context
New Auto-Interp
Negative Logits
Į¨
-0.15
invent
-0.14
ritt
-0.14
rott
-0.14
/read
-0.14
omatic
-0.13
velle
-0.13
quat
-0.13
åŀĤ
-0.13
Ges
-0.13
POSITIVE LOGITS
orz
0.17
zin
0.15
gan
0.14
vine
0.14
enko
0.14
mamak
0.14
ανδ
0.14
ãĤ¤ãĤº
0.14
allis
0.14
μÏĨ
0.14
Activations Density 0.021%