INDEX
Explanations
instances of the word "sleep"
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
492
+0.13
0.4%
1805
+0.13
0.4%
161
+0.13
0.4%
Correlated Neurons
Index
P. Corr.
Cos Sim.
492
+0.13
0.04
1805
+0.13
0.03
1413
+0.13
0.03
Negative Logits
spb
-0.41
ssi
-0.41
DotNetBar
-0.40
Dizziness
-0.40
tagonist
-0.39
swire
-0.39
widetext
-0.38
acd
-0.38
imc
-0.38
drob
-0.37
POSITIVE LOGITS
sleep
1.34
sleep
1.26
Sleep
1.24
slept
1.20
Sleep
1.19
sleeping
1.16
sleeps
1.15
SLEEP
1.14
Sleeping
1.07
Sleeping
1.05
Activations Density 0.084%