INDEX
Explanations
tabular data or structured information
New Auto-Interp
Negative Logits
iltr
-0.18
AZE
-0.17
stanov
-0.16
éri
-0.16
Ñħов
-0.15
-------------</
-0.15
erten
-0.15
riad
-0.15
¦y
-0.15
----------</
-0.14
POSITIVE LOGITS
kp
0.16
columns
0.15
Frid
0.15
_alignment
0.14
column
0.14
balance
0.14
eshire
0.14
Ìĥ
0.14
align
0.14
ushman
0.14
Activations Density 0.005%