INDEX
Explanations
references to LEGO-related content
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
298
+0.11
0.4%
1052
+0.11
0.4%
68
+0.11
0.4%
Correlated Neurons
Index
P. Corr.
Cos Sim.
690
+0.11
0.06
1987
+0.11
0.06
1741
+0.11
0.01
Negative Logits
blackpink
-0.74
RectangleBorder
-0.70
šech
-0.64
oplasmic
-0.60
ⓧ
-0.59
xFFFFFF
-0.58
xffffff
-0.56
relenting
-0.56
ostruct
-0.55
itschrift
-0.53
POSITIVE LOGITS
Augu
0.97
allarg
0.96
Mlle
0.90
affari
0.87
dispen
0.86
abbra
0.86
Godt
0.85
doman
0.85
§.
0.84
effe
0.83
Activations Density 0.436%