INDEX
Explanations
names of individuals, particularly in the context of family relationships and connections
New Auto-Interp
Negative Logits
ÌĨ
-0.17
rych
-0.15
opic
-0.14
uner
-0.13
ô
-0.13
Yayın
-0.13
ÏħÏĩ
-0.13
ussia
-0.13
ISO
-0.13
ôn
-0.13
POSITIVE LOGITS
Jr
0.87
III
0.71
II
0.62
jr
0.60
III
0.56
IV
0.54
junior
0.52
Junior
0.52
II
0.48
jr
0.45
Activations Density 0.075%