INDEX
Explanations
information about events, centers, and unions related to various trades and social movements
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
674
+0.34
1.4%
599
+0.30
1.2%
227
+0.22
0.9%
Correlated Neurons
Index
P. Corr.
Cos Sim.
227
+0.34
0.14
599
+0.30
0.13
1013
+0.22
0.12
Negative Logits
YMMV
-0.66
Witaj
-0.65
Bardzo
-0.64
Kde
-0.63
Cześć
-0.63
Kolor
-0.60
Herzlich
-0.57
Și
-0.57
Dlatego
-0.55
Kiedy
-0.55
POSITIVE LOGITS
<bos>
1.38
省市镇
0.64
onore
0.56
betweenstory
0.53
parut
0.52
dì
0.51
Autoritní
0.48
Jé
0.48
లాలు
0.48
affitto
0.47
Activations Density 2.453%