INDEX
Explanations
mentions of gaming and related terms
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1870
+0.13
0.5%
1865
+0.12
0.4%
893
+0.11
0.4%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1865
+0.13
0.03
1034
+0.12
0.03
893
+0.11
0.03
Negative Logits
uxxxx
-0.53
<>",
-0.53
Geografi
-0.51
BeforeAll
-0.50
aarrggbb
-0.49
ConverterFactory
-0.49
izvē
-0.49
IndentedString
-0.48
StructEnd
-0.47
Addo
-0.47
POSITIVE LOGITS
gaming
1.22
Gaming
1.05
gamer
1.04
gaming
1.00
gamers
0.99
Gaming
0.98
Gam
0.95
GAM
0.89
Gamers
0.89
Gam
0.86
Activations Density 0.101%