INDEX
Explanations
sports-related words related to hockey and football teams and their performance
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1499
+0.09
0.3%
736
+0.09
0.3%
906
+0.09
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
736
+0.09
0.07
1419
+0.09
0.05
175
+0.09
0.06
Negative Logits
branche
-0.65
gela
-0.64
preghiera
-0.61
andaş
-0.60
seduta
-0.58
sved
-0.58
decorazione
-0.57
materie
-0.57
studenti
-0.56
iveau
-0.56
POSITIVE LOGITS
reluct
1.30
shenan
1.26
accla
1.12
indestru
1.09
philanth
1.09
inconce
1.09
maneu
1.07
intersper
1.07
apprehen
1.04
wherea
1.03
Activations Density 0.478%