INDEX
Explanations
Code repository links
The neuron fires on occurrences of “lib” in names (e.g. library, balenalib, base-images), i.e. tokens indicating library or image package references.
New Auto-Interp
Negative Logits
bốn
-0.06
Zion
-0.06
中國
-0.06
elastic
-0.06
mind
-0.06
welcome
-0.06
.Tween
-0.06
drawer
-0.06
multiplier
-0.06
Mid
-0.06
POSITIVE LOGITS
aseg
0.07
Profit
0.07
roku
0.07
olutions
0.07
nedost
0.06
�
0.06
zg
0.06
_pemb
0.06
CENT
0.06
قرار
0.06
Activations Density 0.018%