INDEX
Explanations
the word "engage" in various contexts
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
156
+0.15
0.6%
58
+0.14
0.5%
161
+0.12
0.5%
Correlated Neurons
Index
P. Corr.
Cos Sim.
156
+0.15
0.04
58
+0.14
0.03
161
+0.12
0.02
Negative Logits
pama
-0.54
altrett
-0.48
SizeF
-0.47
zuka
-0.46
Personensuche
-0.45
autorisation
-0.45
ounid
-0.43
guma
-0.43
waw
-0.42
messageInfo
-0.42
POSITIVE LOGITS
engagement
1.33
engage
1.25
Engagement
1.25
Engagement
1.22
engaged
1.17
Engage
1.17
Engaged
1.15
engages
1.14
Engage
1.13
engagement
1.13
Activations Density 0.083%