INDEX
Explanations
The neuron never activates, i.e. it doesn’t detect any pattern in the input.
New Auto-Interp
Negative Logits
<fieldset
-0.08
(out
-0.07
(count
-0.06
結
-0.06
Player
-0.06
された
-0.06
RAW
-0.06
word
-0.06
провер
-0.06
(tab
-0.06
POSITIVE LOGITS
boycott
0.10
boyc
0.07
exceed
0.07
>/
0.07
scant
0.06
蛛
0.06
_REFERER
0.06
Montgomery
0.06
741
0.06
250
0.06
Activations Density 0.002%