INDEX
Explanations
quotes and meta-information related to movie and book scenes
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
50
+0.20
1.5%
82
+0.14
1.0%
1757
+0.13
0.9%
Correlated Neurons
Index
P. Corr.
Cos Sim.
2019
+0.20
0.21
478
+0.14
0.12
381
+0.13
0.06
Negative Logits
<bos>
-3.17
/***
-0.94
springfox
-0.93
ⓧ
-0.87
//};
-0.74
<?
-0.70
<?
-0.68
//});
-0.68
Vegeu
-0.68
AssemblyCompany
-0.68
POSITIVE LOGITS
soulign
0.99
véhic
0.91
quoique
0.91
leanor
0.86
unlaw
0.86
unspeak
0.85
dison
0.84
...."
0.81
soudain
0.80
useRouter
0.80
Activations Density 3.508%