INDEX
Explanations
phrases related to comparison and quantification using the word "relative"
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1677
+0.17
0.6%
1896
+0.12
0.4%
1092
+0.11
0.4%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1677
+0.17
0.03
1306
+0.12
0.02
1092
+0.11
0.02
Negative Logits
Arro
-0.70
Marín
-0.69
philanth
-0.64
Emig
-0.63
Gost
-0.63
Hano
-0.63
OGS
-0.62
enthusi
-0.62
Congreg
-0.61
Sarm
-0.61
POSITIVE LOGITS
relative
1.19
relative
1.08
Relative
1.05
Relative
1.03
RELATIVE
0.79
rel
0.77
rel
0.77
relatives
0.77
relativity
0.70
Rel
0.70
Activations Density 0.051%