INDEX
Explanations
mentions of natural environments and geographical features
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
805
+0.17
0.7%
1870
+0.15
0.6%
1133
+0.13
0.5%
Correlated Neurons
Index
P. Corr.
Cos Sim.
805
+0.17
0.03
1133
+0.15
0.02
1272
+0.13
0.01
Negative Logits
Pued
-0.61
Ceux
-0.59
surpl
-0.56
contribue
-0.55
exti
-0.54
viciss
-0.53
prolon
-0.53
reaf
-0.52
Доброго
-0.52
brille
-0.52
POSITIVE LOGITS
landscape
1.30
Landscape
1.19
Landscape
1.18
landscapes
1.14
landscape
1.14
LANDSCAPE
1.01
Landscapes
0.78
terrain
0.73
landscaping
0.70
terrain
0.70
Activations Density 0.080%