INDEX
Explanations
information related to a social club, including its activities, members, and events
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
227
+0.10
0.3%
509
+0.09
0.3%
81
+0.08
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
81
+0.10
0.02
1786
+0.09
0.00
1551
+0.08
0.03
Negative Logits
broderie
-0.87
bandeau
-0.74
tricot
-0.73
smtplib
-0.72
pymysql
-0.70
flyknit
-0.69
ovate
-0.68
ecru
-0.66
auguri
-0.66
rencont
-0.66
POSITIVE LOGITS
membership
1.16
Membership
1.03
membership
0.93
memberships
0.91
members
0.90
Membership
0.90
member
0.85
Members
0.77
founding
0.67
organization
0.67
Activations Density 0.804%