INDEX
Explanations
timestamps in a description of a sequence of events
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
908
+0.11
0.3%
2010
+0.08
0.2%
690
+0.08
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
908
+0.11
0.02
2010
+0.08
0.04
1859
+0.08
0.03
Negative Logits
disagre
-1.53
maneu
-1.53
indestru
-1.44
affor
-1.43
scrat
-1.42
shenan
-1.41
reluct
-1.41
strick
-1.41
snoopy
-1.40
excru
-1.38
POSITIVE LOGITS
quick
1.33
quickly
1.33
fast
1.27
rapid
1.25
quicker
1.20
faster
1.19
rapidly
1.12
fast
1.09
instant
1.09
nhanh
1.06
Activations Density 0.568%