INDEX
Explanations
instances of the word "cut" used in various contexts
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
376
+0.16
0.9%
351
+0.15
0.8%
380
+0.14
0.8%
Correlated Neurons
Index
P. Corr.
Cos Sim.
351
+0.16
0.01
474
+0.15
0.01
380
+0.14
0.01
Negative Logits
ľ
-2.48
Ī
-2.48
ĸ´
-2.40
¿
-2.36
Ĥ¬
-2.34
ķ
-2.31
§
-2.28
Ĥ
-2.27
¨
-2.27
µ
-2.26
POSITIVE LOGITS
ball
1.81
iem
1.78
iative
1.75
jes
1.72
arie
1.71
maker
1.70
burg
1.69
eness
1.67
imet
1.67
ière
1.65
Activations Density 0.008%