INDEX
Explanations
symbols and representations tied to spiritual or religious contexts
New Auto-Interp
Negative Logits
iao
-0.18
ór
-0.15
279
-0.14
ÛĮات
-0.14
mach
-0.14
atik
-0.13
arias
-0.13
embedding
-0.13
099
-0.13
artifacts
-0.13
POSITIVE LOGITS
symbolic
0.33
symbol
0.33
Symbol
0.32
symbol
0.31
symbolism
0.31
Ñģимвол
0.30
SYMBOL
0.30
Symbol
0.29
.symbol
0.27
metaphor
0.27
Activations Density 0.281%