INDEX
Explanations
phrases containing the word 'hard' followed by a verb in the infinitive form
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
674
+0.11
0.3%
1097
+0.10
0.3%
897
+0.10
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1415
+0.11
0.03
1742
+0.10
0.04
1731
+0.10
0.02
Negative Logits
brille
-0.82
Câ
-0.77
viendra
-0.76
exé
-0.75
obé
-0.72
iyon
-0.71
entraîne
-0.69
parlamento
-0.69
masina
-0.69
kani
-0.68
POSITIVE LOGITS
/**
0.63
imagine
0.61
THISDAY
0.61
JAKARTA
0.60
comprehend
0.59
quantify
0.58
giud
0.57
gage
0.57
slidesPer
0.56
0.56
Activations Density 0.128%