INDEX
Explanations
technical terms related to climate change and environmental impact
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
876
+0.15
0.5%
1120
+0.13
0.4%
1385
+0.13
0.4%
Correlated Neurons
Index
P. Corr.
Cos Sim.
342
+0.15
0.04
1368
+0.13
0.03
1048
+0.13
0.02
Negative Logits
pamph
-0.91
racon
-0.79
dramatist
-0.73
menyen
-0.67
playboy
-0.65
schoolboy
-0.62
burlesque
-0.58
Whigs
-0.57
Machia
-0.57
courtier
-0.57
POSITIVE LOGITS
swarovski
0.78
megane
0.77
[''
0.74
chery
0.73
perfon
0.73
thut
0.72
tranf
0.72
murano
0.71
fep
0.71
nutella
0.70
Activations Density 0.365%