INDEX
Explanations
the occurrence of the substring "ch."
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
369
+0.22
1.3%
410
+0.16
0.9%
2
+0.12
0.7%
Correlated Neurons
Index
P. Corr.
Cos Sim.
2
+0.22
0.03
172
+0.16
0.02
201
+0.12
0.03
Negative Logits
ļ
-2.78
¢
-2.63
Ĥ
-2.55
ľ
-2.53
ĩ
-2.52
»¿
-2.48
į
-2.47
ĸ
-2.47
¡
-2.38
İ
-2.37
POSITIVE LOGITS
icago
1.72
rooms
1.68
ismatic
1.61
induct
1.61
neys
1.54
concluded
1.50
averaged
1.44
expressed
1.43
otype
1.39
iele
1.37
Activations Density 0.041%