INDEX
Explanations
the letter 'K' in various contexts
New Auto-Interp
Negative Logits
اÙĨ
-0.16
alen
-0.15
alon
-0.15
íļĮ
-0.14
ature
-0.14
uxe
-0.14
593
-0.13
Å¡tÃŃ
-0.13
igest
-0.13
reuse
-0.13
POSITIVE LOGITS
rypton
0.18
erk
0.15
bler
0.15
logg
0.14
bie
0.14
ront
0.14
feld
0.14
osit
0.14
еÑĪ
0.14
ayi
0.14
Activations Density 0.069%