INDEX
Explanations
references to fundraising and charitable activities
New Auto-Interp
Negative Logits
zel
-0.15
aket
-0.14
esi
-0.14
_office
-0.14
volunteers
-0.14
âĶģ
-0.14
agit
-0.13
oÄŁ
-0.13
morb
-0.13
ève
-0.13
POSITIVE LOGITS
charities
0.27
causes
0.27
charity
0.24
Multiple
0.22
cancer
0.20
Causes
0.20
char
0.20
animal
0.18
Multiple
0.18
children
0.18
Activations Density 0.145%