INDEX
Explanations
The neuron fires on technical terms and jargon related to nuclear reactors (e.g. reactor, nuclear, fissile, moderator, coolant, combustible).
New Auto-Interp
Negative Logits
üle
-0.07
ifold
-0.06
ship
-0.06
puzzle
-0.06
_properties
-0.06
="#">
-0.06
Naz
-0.06
liste
-0.06
manufact
-0.06
Pathfinder
-0.06
POSITIVE LOGITS
.setBackgroundResource
0.07
REDIS
0.07
IconButton
0.06
�
0.06
σσα
0.06
틀
0.06
西
0.06
NSNumber
0.06
pager
0.06
层
0.06
Activations Density 0.006%