INDEX
Explanations
baseball-related terms and actions
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1870
+0.11
0.3%
868
+0.10
0.3%
2034
+0.10
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
868
+0.11
0.05
400
+0.10
0.04
756
+0.10
0.04
Negative Logits
encomp
-1.19
intersper
-1.16
increa
-1.09
reluct
-1.07
alberto
-1.06
javier
-1.03
impra
-1.01
sergio
-0.99
emphat
-0.99
depic
-0.99
POSITIVE LOGITS
gyhoeddwyd
0.71
insuffisamment
0.66
חיצוניים
0.66
تانيه
0.58
insee
0.58
AsUp
0.56
aprilie
0.56
úgó
0.55
มาะ
0.55
UVWXYZ
0.55
Activations Density 0.250%