INDEX
Explanations
information related to sports events, including match details and teams
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
2019
+0.40
1.4%
304
+0.16
0.6%
1870
+0.14
0.5%
Correlated Neurons
Index
P. Corr.
Cos Sim.
2019
+0.40
0.04
924
+0.16
0.03
1678
+0.14
0.02
Negative Logits
unspeak
-1.50
shenan
-1.45
impra
-1.44
horrend
-1.44
snoopy
-1.43
tolerably
-1.41
hentai
-1.40
gaily
-1.39
stickied
-1.37
apprehen
-1.37
POSITIVE LOGITS
<bos>
1.24
meras
1.06
manuten
1.01
alkoh
1.00
Kategor
0.96
keramik
0.95
bunda
0.93
solidar
0.92
prostitu
0.90
utop
0.90
Activations Density 0.072%