INDEX
Explanations
First person plural
discussions about societal roles and expectations related to women and gender.
This neuron responds to first‐person plural pronouns (we, us).
New Auto-Interp
Negative Logits
torch
-0.07
flowers
-0.06
lexer
-0.06
VERN
-0.06
осіб
-0.06
بلند
-0.06
.Se
-0.06
ве
-0.06
papers
-0.06
LOB
-0.06
POSITIVE LOGITS
skvěl
0.06
неск
0.06
pinned
0.06
!";↵
0.06
0.06
'; ↵
0.06
↵
0.06
wreak
0.06
sw
0.06
leží
0.06
Activations Density 0.046%