INDEX
Explanations
references to specific ethnic groups or the concept of ethnicity in a document
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
521
+0.13
0.5%
1677
+0.12
0.4%
313
+0.12
0.4%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1677
+0.13
0.02
1971
+0.12
0.02
521
+0.12
0.02
Negative Logits
awtextra
-0.55
Palmar
-0.51
rceil
-0.49
GINIA
-0.47
ToolStripButton
-0.47
Economía
-0.46
Tē
-0.45
Erreferentziak
-0.45
Istorija
-0.43
Demografía
-0.43
POSITIVE LOGITS
ethnic
1.15
Ethnic
1.11
ethnicity
1.00
Ethnic
0.99
tanong
0.93
ethnic
0.93
eth
0.92
Ethnicity
0.82
Mlle
0.82
Whence
0.80
Activations Density 0.076%