INDEX
Explanations
phrases related to computer hardware specifications and deals
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
341
+0.10
0.3%
757
+0.09
0.3%
32
+0.09
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
690
+0.10
0.04
1120
+0.09
0.03
1343
+0.09
0.03
Negative Logits
prevent
-0.56
push
-0.55
fået
-0.55
strike
-0.54
ידה
-0.53
neod
-0.53
odb
-0.53
odm
-0.53
opty
-0.53
cur
-0.52
POSITIVE LOGITS
Dell
2.00
Dell
1.70
DELL
1.55
Abbé
1.40
Bibl
1.15
lele
1.12
fluo
1.09
Mlle
1.08
magis
1.08
Intere
1.08
Activations Density 0.279%