INDEX
Explanations
information related to pregnancy
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1602
+0.13
0.4%
486
+0.12
0.4%
481
+0.11
0.4%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1602
+0.13
0.02
1105
+0.12
0.02
260
+0.11
0.02
Negative Logits
dovr
-0.64
Pourtant
-0.59
Toutefois
-0.56
Jusqu
-0.55
toprule
-0.53
widetext
-0.53
Manufact
-0.52
Sklici
-0.52
Ceux
-0.52
noct
-0.50
POSITIVE LOGITS
pregnancy
1.12
pregnant
1.09
pregnant
0.93
Pregnancy
0.92
Pregnancy
0.91
Pregnant
0.85
pregnancy
0.83
pregnancies
0.82
PREG
0.75
PREG
0.71
Activations Density 0.062%