INDEX
Explanations
references to biblical studies and semantics
New Auto-Interp
Negative Logits
rodin
-0.18
orrow
-0.15
Tao
-0.15
æ·
-0.15
oky
-0.15
arac
-0.15
Chap
-0.15
Quotes
-0.15
anter
-0.14
rous
-0.14
POSITIVE LOGITS
exe
0.25
NT
0.21
exe
0.19
NT
0.19
Anchor
0.18
Interpreter
0.17
Anchor
0.17
Interpreter
0.16
Palestinian
0.16
Klopp
0.15
Activations Density 0.060%