INDEX
Explanations
references to Jewish culture and traditions
New Auto-Interp
Negative Logits
Christ
-0.19
aldi
-0.17
arian
-0.17
christ
-0.17
christ
-0.16
mgr
-0.15
æİĴ
-0.15
Verfüg
-0.15
eller
-0.15
abic
-0.15
POSITIVE LOGITS
tz
0.22
mit
0.22
Mahar
0.21
Hash
0.20
Bris
0.19
Reb
0.19
578
0.18
577
0.18
Minh
0.18
hal
0.18
Activations Density 0.101%