INDEX
Explanations
names of prominent individuals or characters associated with significant events or topics
New Auto-Interp
Head Attr Weights
0:0.11
1:0.04
2:0.19
3:0.08
4:0.16
5:0.04
6:0.03
7:0.03
8:0.04
9:0.13
10:0.06
11:0.03
Negative Logits
yip
-1.36
creek
-1.25
cipled
-1.17
arks
-1.15
Tradable
-1.15
ciplinary
-1.13
actionGroup
-1.10
IONS
-1.10
viewership
-1.10
specificity
-1.10
POSITIVE LOGITS
ROR
1.60
ère
1.33
Duchess
1.30
ヘ
1.19
iste
1.18
nun
1.18
christ
1.18
bourg
1.16
Pry
1.15
etter
1.15
Activations Density 0.002%