INDEX
Explanations
phrases related to skills or abilities
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
198
+0.13
0.4%
50
+0.11
0.3%
16
+0.07
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
16
+0.13
0.06
92
+0.11
0.04
1664
+0.07
0.03
Negative Logits
stör
-0.72
kompati
-0.60
bemer
-0.59
sokak
-0.54
<bos>
-0.54
dör
-0.52
WindowConstants
-0.52
ppé
-0.51
Entreprises
-0.51
preciosas
-0.51
POSITIVE LOGITS
pylab
0.66
hashlib
0.65
skimage
0.63
pymysql
0.63
pymongo
0.62
mène
0.62
heapq
0.60
tempfile
0.59
psycopg
0.59
étu
0.58
Activations Density 0.341%