INDEX
Explanations
The neuron fires on expressions of absence or unavailability (e.g. “there are no…” statements).
New Auto-Interp
Negative Logits
الموس
-0.07
Early
-0.07
.TEXT
-0.06
بول
-0.06
ש
-0.06
_keyboard
-0.06
-Cs
-0.06
nghị
-0.06
_Arg
-0.06
_dimensions
-0.06
POSITIVE LOGITS
قطع
0.07
0.07
ilm
0.06
ICollection
0.06
unfinished
0.06
Fabric
0.06
dů
0.06
Gospel
0.06
ExecutionContext
0.06
unbiased
0.06
Activations Density 0.029%