INDEX
Explanations
sports-related terms or phrases, particularly related to team movements and events
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1042
+0.14
0.4%
1177
+0.11
0.3%
939
+0.09
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
223
+0.14
0.03
53
+0.11
0.01
455
+0.09
0.01
Negative Logits
heapq
-0.99
smtplib
-0.96
hashlib
-0.84
pylab
-0.83
psycopg
-0.75
pymysql
-0.74
shutil
-0.73
viewDid
-0.72
functools
-0.71
zipfile
-0.69
POSITIVE LOGITS
Fais
0.72
Seni
0.72
philanth
0.66
Keny
0.63
Pende
0.63
ausp
0.63
susun
0.63
franchise
0.63
Senat
0.62
Khart
0.62
Activations Density 0.575%