INDEX
Explanations
thoughts and dialogue
This neuron specializes in detecting Spanish-language words.
New Auto-Interp
Negative Logits
ystems
-0.06
Te
-0.06
ewan
-0.06
85
-0.06
OS
-0.06
671
-0.06
cores
-0.06
score
-0.06
theta
-0.06
82
-0.06
POSITIVE LOGITS
Crypt
0.07
unterschied
0.06
спіл
0.06
_radi
0.06
domácí
0.06
ái
0.06
Cod
0.06
convoy
0.06
=";↵
0.06
↵↵
0.06
Activations Density 0.040%