INDEX
Explanations
negative sentiment or criticism in reviews or opinions
New Auto-Interp
Head Attr Weights
0:0.09
1:0.05
2:0.08
3:0.03
4:0.02
5:0.04
6:0.05
7:0.03
8:0.08
9:0.03
10:0.17
11:0.27
Negative Logits
osponsors
-2.68
ospons
-2.47
guiIcon
-2.28
luaj
-2.24
ⓘ
-2.21
jen
-2.19
assetsadobe
-2.16
Preview
-2.08
サーティワン
-2.07
Contrast
-2.06
POSITIVE LOGITS
Ezra
2.29
Xan
2.11
Circle
2.06
Berry
2.01
Ariel
1.99
Square
1.90
Malk
1.89
Nir
1.88
addictive
1.87
Avalon
1.81
Activations Density 0.001%