INDEX
Explanations
phrases that emphasize the importance of accuracy
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
156
+0.21
1.2%
148
+0.15
0.9%
376
+0.14
0.8%
Correlated Neurons
Index
P. Corr.
Cos Sim.
407
+0.21
0.02
79
+0.15
0.02
86
+0.14
0.02
Negative Logits
aker
-1.77
renn
-1.55
acker
-1.54
itian
-1.51
orian
-1.48
ori
-1.48
urer
-1.47
ker
-1.47
obacterium
-1.46
ussels
-1.45
POSITIVE LOGITS
ŀ
3.10
¥
3.02
ģ
2.99
¡
2.97
Ļ
2.88
«
2.79
ĻĤ
2.77
Ģ
2.75
µ
2.75
ļ
2.75
Activations Density 0.015%