INDEX
Explanations
mentions of charitable events and fundraising activities
New Auto-Interp
Negative Logits
Bilim
-0.15
Routine
-0.15
.Buffer
-0.14
ayet
-0.14
esz
-0.14
Ranked
-0.14
ftar
-0.13
ocity
-0.13
byt
-0.13
gov
-0.13
POSITIVE LOGITS
silent
0.35
Silent
0.32
r
0.30
silent
0.29
Sil
0.25
door
0.24
proceeds
0.23
-ra
0.23
fundraiser
0.22
Proceed
0.21
Activations Density 0.045%