INDEX
Explanations
instances of the phrase "backing up."
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
439
+0.11
0.6%
455
+0.10
0.6%
222
+0.10
0.5%
Correlated Neurons
Index
P. Corr.
Cos Sim.
297
+0.11
0.09
95
+0.10
0.09
399
+0.10
0.08
Negative Logits
sworth
-1.82
lands
-1.78
stro
-1.59
dered
-1.59
bery
-1.58
beat
-1.54
shire
-1.53
tle
-1.49
orious
-1.49
imming
-1.49
POSITIVE LOGITS
interface
1.61
respectively
1.61
age
1.59
Soci
1.46
ylon
1.45
Discussion
1.45
Devices
1.42
Biomed
1.42
Convention
1.41
interfaces
1.38
Activations Density 0.108%