INDEX
Explanations
representations of sounds and their descriptions in the environment
New Auto-Interp
Negative Logits
hear
-0.20
apiro
-0.17
hearing
-0.17
Hearth
-0.15
pes
-0.15
145
-0.15
289
-0.15
ekim
-0.15
imon
-0.14
826
-0.14
POSITIVE LOGITS
throat
0.17
nasal
0.17
gut
0.15
calls
0.15
.call
0.15
serie
0.15
chip
0.15
-cache
0.15
IMIT
0.15
call
0.15
Activations Density 0.019%