INDEX
Explanations
The neuron detects occurrences of the word “uterine.”
New Auto-Interp
Negative Logits
accol
-0.07
cu
-0.06
FullScreen
-0.06
.review
-0.06
иля
-0.06
.code
-0.06
تف
-0.06
่ได
-0.06
582
-0.06
DI
-0.06
POSITIVE LOGITS
uterus
0.10
utter
0.09
womb
0.08
här
0.08
rotary
0.08
ruling
0.07
labor
0.07
-U
0.07
gutter
0.06
undertaken
0.06
Activations Density 0.003%