INDEX
Explanations
mentions of the word "fellow"
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
168
+0.13
0.4%
198
+0.13
0.4%
1145
+0.12
0.4%
Correlated Neurons
Index
P. Corr.
Cos Sim.
168
+0.13
0.02
198
+0.13
0.02
29
+0.12
0.02
Negative Logits
__]
-0.58
<=",
-0.46
AttributeSet
-0.46
LinkId
-0.46
OCCURRED
-0.45
***!
-0.45
Evaporation
-0.45
RTSC
-0.44
OMITBAD
-0.44
),),
-0.44
POSITIVE LOGITS
Áng
0.93
Mónica
0.88
FELLOW
0.86
viciss
0.85
Darío
0.84
Fellow
0.84
fellow
0.83
Minang
0.82
peculi
0.79
Palembang
0.78
Activations Density 0.056%