INDEX
Explanations
phrases related to economic activities and events
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
2034
+0.21
0.6%
382
+0.14
0.4%
1535
+0.13
0.4%
Correlated Neurons
Index
P. Corr.
Cos Sim.
382
+0.21
0.13
1917
+0.14
0.08
195
+0.13
0.10
Negative Logits
guangdong
-0.73
Faites
-0.65
blusa
-0.64
Zdra
-0.64
Vrij
-0.58
Quiénes
-0.58
taget
-0.57
quidem
-0.57
jums
-0.57
えたら
-0.57
POSITIVE LOGITS
wherea
1.24
depic
1.19
lts
1.12
fortn
1.11
secon
1.08
indestru
1.07
Venise
1.06
tremb
1.06
encomp
1.05
fff
1.03
Activations Density 0.706%