INDEX
Explanations
mentions of the word "sex."
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
866
+0.12
0.4%
687
+0.12
0.4%
892
+0.11
0.4%
Correlated Neurons
Index
P. Corr.
Cos Sim.
866
+0.12
0.02
101
+0.12
0.02
313
+0.11
0.02
Negative Logits
RetentionPolicy
-0.52
dient
-0.50
ManagedBean
-0.50
WinForms
-0.49
Dieter
-0.49
mybatisplus
-0.49
presidente
-0.49
UnitTesting
-0.48
WaitGroup
-0.47
Presidente
-0.47
POSITIVE LOGITS
sex
1.22
Sex
1.12
Sex
1.11
SEX
1.09
sex
1.01
exé
0.95
SEX
0.90
relenting
0.88
McLaugh
0.86
mistak
0.85
Activations Density 0.039%