INDEX
Explanations
Justice/Consequences
The neuron detects words and phrases expressing that someone “deserves” or “got what they deserved” (i.e., notions of deserved retribution or consequences).
New Auto-Interp
Negative Logits
_change
-0.07
.Sample
-0.07
-->↵↵
-0.07
Authenticated
-0.07
qint
-0.06
Kid
-0.06
Lic
-0.06
Appending
-0.06
airy
-0.06
mansion
-0.06
POSITIVE LOGITS
.mapper
0.07
柜
0.06
.recyclerview
0.06
Currency
0.06
dbo
0.06
supposedly
0.06
парт
0.06
UGH
0.06
uży
0.06
ویکی
0.06
Activations Density 0.016%