INDEX
Explanations
This neuron activates on German words or phrases (marking passages written in German).
New Auto-Interp
Negative Logits
Wheels
-0.07
zv
-0.07
vict
-0.06
annotations
-0.06
td
-0.06
держав
-0.06
UpdatedAt
-0.06
(vis
-0.06
św
-0.06
"As
-0.06
POSITIVE LOGITS
operator
0.07
στους
0.07
(random
0.07
amazon
0.06
.place
0.06
SQLException
0.06
_parser
0.06
reduce
0.06
ction
0.06
jogador
0.06
Activations Density 0.039%