INDEX
Explanations
legal terminology and concepts related to jury selection and behavior
New Auto-Interp
Negative Logits
dezelve
-0.69
myſelf
-0.64
MainAxisSize
-0.60
TextAppearance
-0.59
zelve
-0.59
ſind
-0.57
ftagPool
-0.57
ſche
-0.56
ſever
-0.55
ſelves
-0.54
POSITIVE LOGITS
ono
0.40
ümmer
0.40
Basically
0.40
Basically
0.39
shitty
0.38
ks
0.38
bad
0.38
cs
0.38
kje
0.38
crappy
0.37
Activations Density 0.505%