INDEX
Explanations
the preposition "in" in various contexts
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
95
+0.12
0.7%
69
+0.11
0.7%
159
+0.11
0.7%
Correlated Neurons
Index
P. Corr.
Cos Sim.
69
+0.12
0.02
194
+0.11
0.01
249
+0.11
0.01
Negative Logits
stained
-1.56
eter
-1.50
raits
-1.48
er
-1.43
fans
-1.41
_[
-1.37
waves
-1.36
reminds
-1.35
eur
-1.34
ouin
-1.29
POSITIVE LOGITS
ĥ½
1.89
completion
1.49
fact
1.49
ousand
1.44
:=
1.40
vasive
1.40
compliance
1.38
applic
1.37
fileID
1.34
clusion
1.33
Activations Density 0.039%