INDEX
Explanations
actions related to collecting items or data
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1166
+0.09
0.3%
1379
+0.09
0.3%
1482
+0.09
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
369
+0.09
0.03
667
+0.09
0.03
849
+0.09
0.03
Negative Logits
défend
-0.73
reconnaît
-0.63
Viene
-0.62
cassert
-0.59
renfer
-0.58
soutient
-0.57
résulte
-0.55
prévoit
-0.55
nomme
-0.54
révèle
-0.53
POSITIVE LOGITS
collect
1.03
collect
0.86
Collect
0.86
collects
0.86
collected
0.85
collecting
0.83
COLLECT
0.82
collected
0.82
gather
0.79
collecting
0.76
Activations Density 0.229%