INDEX
Explanations
phrases related to charitable causes and fundraising efforts
New Auto-Interp
Negative Logits
yas
-0.16
å±Ĭ
-0.15
577
-0.15
Li
-0.15
base
-0.14
oden
-0.14
SizePolicy
-0.14
ourn
-0.14
lace
-0.14
IPP
-0.14
POSITIVE LOGITS
causes
0.36
cause
0.32
Causes
0.31
Cause
0.28
charities
0.26
Cause
0.26
worthy
0.26
cause
0.26
causa
0.23
charity
0.23
Activations Density 0.177%