INDEX
Explanations
references to small or diminutive things
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
50
+0.18
1.1%
1983
+0.11
0.7%
241
+0.11
0.6%
Correlated Neurons
Index
P. Corr.
Cos Sim.
241
+0.18
0.06
920
+0.11
0.06
1983
+0.11
0.05
Negative Logits
<bos>
-3.11
/***
-1.06
ⓧ
-0.88
<?
-0.76
-0.75
//---
-0.74
//};
-0.73
<?
-0.71
})();
-0.69
///**
-0.67
POSITIVE LOGITS
tramont
1.14
franz
1.12
stockholm
1.12
lill
1.10
bayern
1.09
Minang
1.06
wien
1.06
maroc
1.05
little
1.04
mef
1.04
Activations Density 0.104%