INDEX
Explanations
instances of numbers and references to images or visual elements
New Auto-Interp
Head Attr Weights
0:0.03
1:0.03
2:0.06
3:0.15
4:0.07
5:0.06
6:0.22
7:0.02
8:0.06
9:0.11
10:0.09
11:0.05
Negative Logits
behav
-1.24
iod
-1.23
Rai
-1.22
lapt
-1.21
[|
-1.20
��
-1.16
subcontract
-1.14
cknow
-1.13
ADRA
-1.13
isation
-1.12
POSITIVE LOGITS
tags
1.58
love
1.48
hello
1.39
oji
1.38
aru
1.36
cellence
1.35
justice
1.31
reality
1.27
Reader
1.26
liber
1.25
Activations Density 0.227%