INDEX
Explanations
references to specific provinces, locations, and events
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
227
+0.10
0.3%
1499
+0.10
0.3%
395
+0.09
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
227
+0.10
0.06
395
+0.10
0.04
20
+0.09
0.04
Negative Logits
chong
-1.29
kyo
-1.28
guarante
-1.26
XIA
-1.26
bangkok
-1.26
increa
-1.20
chrysler
-1.20
seoul
-1.19
chande
-1.19
eyel
-1.18
POSITIVE LOGITS
antd
0.82
Bei
0.68
mybatisplus
0.65
China
0.65
Bei
0.64
Chinese
0.63
Dazu
0.62
China
0.62
Xinhua
0.61
Chinese
0.60
Activations Density 0.254%