INDEX
Explanations
verbs related to cause and effect or action and result relationships
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1013
+0.10
0.3%
645
+0.10
0.3%
198
+0.09
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1142
+0.10
0.05
460
+0.10
0.04
1823
+0.09
0.04
Negative Logits
setImageBitmap
-0.52
NewUrlParser
-0.50
errHandler
-0.49
ğaz
-0.49
ekw
-0.48
mergeFrom
-0.48
fillType
-0.45
columnNumber
-0.45
kulu
-0.45
AutoScaleMode
-0.45
POSITIVE LOGITS
nutella
0.76
lidl
0.74
michelin
0.71
dovr
0.70
tiffany
0.70
onor
0.69
fermo
0.69
peppa
0.68
afront
0.68
marcato
0.68
Activations Density 0.297%