INDEX
Explanations
words that express kindness and generosity
New Auto-Interp
Negative Logits
oplan
-0.15
ixel
-0.15
ennis
-0.15
enger
-0.14
ting
-0.14
Clr
-0.14
ihn
-0.14
_DEFINE
-0.14
oras
-0.14
si
-0.13
POSITIVE LOGITS
*time
0.15
lest
0.15
fal
0.14
UCKET
0.14
ASA
0.14
gesture
0.14
udge
0.14
ÙĨÙĤد
0.13
venes
0.13
pton
0.13
Activations Density 0.073%