INDEX
Explanations
instances of the pronoun "they."
New Auto-Interp
Negative Logits
agne
-0.17
ecture
-0.15
ActionTypes
-0.15
Their
-0.15
uito
-0.15
their
-0.15
ئت
-0.15
edla
-0.14
HOLDER
-0.14
ocos
-0.14
POSITIVE LOGITS
said
0.17
say
0.17
saying
0.16
Aut
0.15
call
0.15
orn
0.15
-call
0.14
bern
0.14
Call
0.14
vik
0.14
Activations Density 0.160%