INDEX
Explanations
dates in the format "Month, Year" with high activation values
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1978
+0.18
0.6%
382
+0.16
0.5%
1870
+0.12
0.4%
Correlated Neurons
Index
P. Corr.
Cos Sim.
636
+0.18
0.04
48
+0.16
0.04
1187
+0.12
0.03
Negative Logits
heapq
-0.67
Nichts
-0.63
rospy
-0.61
astéro
-0.60
[''],
-0.59
Gambas
-0.59
אין
-0.59
المنا
-0.59
asteroide
-0.56
pymongo
-0.56
POSITIVE LOGITS
sement
0.83
1
0.82
monaster
0.77
frambo
0.76
kön
0.76
marte
0.76
meras
0.75
vitale
0.71
vermel
0.71
utop
0.71
Activations Density 0.058%