INDEX
Explanations
This neuron fires on mentions of the operating system name “Linux.”
New Auto-Interp
Negative Logits
otive
-0.07
取
-0.07
sought
-0.06
Rat
-0.06
nid
-0.06
BX
-0.06
Bom
-0.06
天
-0.06
VIDEO
-0.06
mans
-0.06
POSITIVE LOGITS
Bootstrap
0.08
láda
0.07
yıldır
0.07
Chevrolet
0.07
Lv
0.07
Wildlife
0.06
ализа
0.06
)','
0.06
capacidad
0.06
naming
0.06
Activations Density 0.008%