INDEX
Explanations
mathematical equations or expressions
New Auto-Interp
Negative Logits
uci
-0.17
{@-0.17
aign
-0.17
bjerg
-0.15
emer
-0.15
Bot
-0.15
bud
-0.14
lush
-0.14
bot
-0.14
vice
-0.14
POSITIVE LOGITS
Big
0.23
Big
0.22
left
0.21
left
0.19
big
0.19
bigint
0.18
BIG
0.18
big
0.17
BIG
0.17
-big
0.17
Activations Density 0.340%