INDEX
Explanations
references to specific parks and locations
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
477
+0.15
0.9%
156
+0.13
0.7%
46
+0.12
0.7%
Correlated Neurons
Index
P. Corr.
Cos Sim.
477
+0.15
0.03
145
+0.13
0.03
30
+0.12
0.02
Negative Logits
ĥ½
-3.47
ķ
-3.29
ĵ
-3.19
·
-3.14
§
-3.00
ĩ
-2.96
Ĥ
-2.92
ģ
-2.89
¶
-2.89
¦
-2.88
POSITIVE LOGITS
hurst
2.46
inson
2.38
ways
2.23
way
2.23
holder
1.93
ings
1.92
view
1.92
bell
1.85
yard
1.85
ing
1.82
Activations Density 0.198%