INDEX
Explanations
The neuron activates on mentions of the Linux distribution “Arch Linux.”
New Auto-Interp
Negative Logits
deck
-0.07
Marg
-0.07
Bark
-0.06
Eng
-0.06
izations
-0.06
Beg
-0.06
VA
-0.06
ashes
-0.06
маз
-0.06
Siber
-0.06
POSITIVE LOGITS
recursively
0.06
(KeyCode
0.06
escort
0.06
khuyến
0.06
くん
0.06
oluş
0.06
dein
0.06
高校
0.06
Assoc
0.06
_gp
0.06
Activations Density 0.002%