INDEX
Explanations
references to legal proceedings and testimonies
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
674
+0.12
0.4%
184
+0.08
0.2%
344
+0.08
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1395
+0.12
0.04
707
+0.08
0.04
1030
+0.08
0.02
Negative Logits
swarovski
-0.92
tupperware
-0.84
hairc
-0.82
nutella
-0.79
philips
-0.76
tricot
-0.74
embodi
-0.73
oreo
-0.72
ecru
-0.72
arture
-0.71
POSITIVE LOGITS
today
1.05
now
0.96
today
0.90
now
0.85
tonight
0.85
Today
0.79
Today
0.79
Now
0.74
current
0.74
Now
0.73
Activations Density 0.536%