INDEX
Explanations
information related to updates in a specific game or program
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1577
+0.45
2.0%
1842
+0.28
1.2%
394
+0.25
1.1%
Correlated Neurons
Index
P. Corr.
Cos Sim.
184
+0.45
0.10
1577
+0.28
0.16
1842
+0.25
0.12
Negative Logits
shenan
-1.88
encomp
-1.85
impra
-1.82
unspeak
-1.80
reluct
-1.80
affor
-1.79
indestru
-1.78
maneu
-1.71
increa
-1.70
scrat
-1.69
POSITIVE LOGITS
MessageTagHelper
0.58
)).
0.54
.
0.53
WriteTagHelper
0.52
.
0.52
0.52
}}}{\0.52
fieldNum
0.51
bibfnamefont
0.51
BoxFit
0.51
Activations Density 2.787%