INDEX
Explanations
chemical compounds involving silver
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
876
+0.25
0.8%
283
+0.11
0.4%
1120
+0.10
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
736
+0.25
0.05
876
+0.11
-0.01
1368
+0.10
0.03
Negative Logits
pamph
-1.25
racon
-1.04
Krzysz
-0.99
philanth
-0.96
shenan
-0.94
Città
-0.91
Jurist
-0.91
courtier
-0.89
schoolmaster
-0.89
porno
-0.88
POSITIVE LOGITS
[''
0.70
'\''
0.66
hansen
0.63
citroen
0.63
foon
0.63
auctor
0.63
cæ
0.61
getJSON
0.61
waer
0.60
feen
0.60
Activations Density 0.273%