INDEX
Explanations
the preposition "from" in various contexts
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
69
+0.13
0.7%
85
+0.13
0.7%
326
+0.11
0.6%
Correlated Neurons
Index
P. Corr.
Cos Sim.
69
+0.13
0.04
493
+0.13
0.02
62
+0.11
0.02
Negative Logits
increment
-1.54
cycle
-1.47
pause
-1.46
meter
-1.43
embargo
-1.39
stro
-1.38
decis
-1.34
tempo
-1.34
-->
-1.34
spins
-1.33
POSITIVE LOGITS
oxin
1.84
©
1.79
affin
1.71
apine
1.67
uk
1.65
ondon
1.64
ĻĤ
1.64
quette
1.61
tgz
1.60
nj
1.56
Activations Density 0.161%