INDEX
Explanations
words related to reviewing or critiquing various forms of media or art
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
251
+0.11
0.4%
1438
+0.10
0.3%
1363
+0.10
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
251
+0.11
0.03
1847
+0.10
0.02
1865
+0.10
0.02
Negative Logits
Geographie
-0.47
iyon
-0.45
loride
-0.44
habet
-0.44
mús
-0.43
getStart
-0.41
viewWillAppear
-0.41
vost
-0.41
Composable
-0.40
FloatField
-0.40
POSITIVE LOGITS
EVER
0.91
ever
0.86
Ever
0.76
EVER
0.75
Ever
0.73
ⓧ
0.68
ever
0.68
dichi
0.65
gardien
0.63
jamás
0.62
Activations Density 0.065%