INDEX
Explanations
phrases related to sports statistics and team performance
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1445
+0.11
0.3%
690
+0.09
0.3%
382
+0.09
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
736
+0.11
0.08
382
+0.09
0.06
1445
+0.09
0.07
Negative Logits
wien
-1.33
affez
-1.31
meis
-1.28
aquare
-1.22
mef
-1.21
gmbh
-1.17
NOO
-1.16
myn
-1.16
milano
-1.13
fup
-1.12
POSITIVE LOGITS
earned
0.75
earning
0.64
deserved
0.62
congratulated
0.59
winning
0.59
earn
0.58
hailed
0.58
helped
0.57
achieved
0.57
became
0.57
Activations Density 0.694%