INDEX
Explanations
The neuron strongly activates on terms referring to the mother (and related maternal health) in medical or pregnancy‐related contexts.
New Auto-Interp
Negative Logits
Callback
-0.07
加载
-0.06
DatePicker
-0.06
inkel
-0.06
List
-0.06
буд
-0.06
(Component
-0.06
istol
-0.06
BTTag
-0.06
FAT
-0.06
POSITIVE LOGITS
Writes
0.07
nedenle
0.07
ffects
0.06
-news
0.06
.MIN
0.06
ному
0.06
Prior
0.06
-sama
0.06
erosion
0.06
vyh
0.06
Activations Density 0.008%