INDEX
Explanations
timestamps and numerical data
New Auto-Interp
Negative Logits
esda
-0.16
356
-0.15
nock
-0.15
retty
-0.15
Beit
-0.15
Escorts
-0.15
Hubb
-0.14
arness
-0.14
desi
-0.14
aukee
-0.14
POSITIVE LOGITS
ardo
0.16
Baz
0.15
bau
0.15
rou
0.15
elian
0.14
'''
0.14
ified
0.14
άνι
0.14
baz
0.14
PÅĻed
0.14
Activations Density 0.043%