INDEX

Explanations

TV, broadcast, airs, televised

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

什么样的

-1.46

別の

-1.37

 وكانت

-1.25

koliv

-1.22

廚房

-1.21

 وكان

-1.21

 maç

-1.16

 yüksek

-1.15

 болез

-1.15

ίας

-1.13

POSITIVE LOGITS

 will

1.70

and

1.45

but

1.39

ve

1.32



1.29

 again

1.24

 isolado

1.23

 исти

1.20

we

1.18

 still

1.18

Activations Density 0.029%