INDEX
Explanations
attributes related to user interface components in code
New Auto-Interp
Negative Logits
lick
-0.16
iena
-0.15
anmar
-0.14
loub
-0.14
Obr
-0.14
ckett
-0.14
969
-0.14
imon
-0.14
inka
-0.14
illet
-0.14
POSITIVE LOGITS
fa
0.26
fas
0.21
Fa
0.18
RIX
0.18
fas
0.18
oir
0.16
.fa
0.16
icon
0.16
fa
0.16
mdi
0.16
Activations Density 0.009%