INDEX
Explanations
personal experiences and stories related to relationships and challenges
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
381
+0.17
0.5%
184
+0.17
0.5%
1013
+0.13
0.4%
Correlated Neurons
Index
P. Corr.
Cos Sim.
184
+0.17
0.04
1533
+0.17
0.02
1445
+0.13
0.07
Negative Logits
sappi
-1.59
mef
-1.50
lidl
-1.47
dises
-1.47
toledo
-1.47
daf
-1.45
chery
-1.45
stockholm
-1.44
vogli
-1.44
afp
-1.42
POSITIVE LOGITS
my
0.90
I
0.89
wasn
0.86
was
0.84
afterwards
0.75
had
0.74
when
0.74
didn
0.74
went
0.74
then
0.72
Activations Density 0.591%