INDEX
Explanations
project names or identifiers associated with specific entities
New Auto-Interp
Head Attr Weights
0:0.02
1:0.03
2:0.05
3:0.04
4:0.04
5:0.05
6:0.48
7:0.03
8:0.05
9:0.05
10:0.06
11:0.04
Negative Logits
ּ
-1.56
glasses
-1.32
Haku
-1.25
folders
-1.22
=-=-=-=-=-=-=-=-
-1.19
ONSORED
-1.17
hetti
-1.14
remotely
-1.14
_-
-1.13
stitching
-1.11
POSITIVE LOGITS
helm
1.58
wart
1.51
eus
1.45
ngth
1.38
aditional
1.34
avan
1.33
encia
1.30
ober
1.28
ê
1.27
pard
1.25
Activations Density 0.032%