INDEX
Explanations
numerical data and statistical values
New Auto-Interp
Negative Logits
.Paths
-0.15
Nin
-0.15
_softc
-0.14
Busty
-0.14
oust
-0.14
tile
-0.14
equ
-0.14
ActionTypes
-0.14
ÑĢел
-0.14
_VC
-0.14
POSITIVE LOGITS
132
0.37
136
0.36
13
0.36
139
0.36
134
0.35
128
0.35
138
0.34
131
0.34
133
0.34
130
0.33
Activations Density 0.029%