INDEX

Explanations

connecting discourse markers

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

 also

-1.93

but

-1.74

 myös

-1.52

 также

-1.43

但是

-1.34

 these

-1.28

 แต่

-1.23

 También

-1.20

 også

-1.20

还有

-1.20

POSITIVE LOGITS

というわけで

1.27

ということで

1.24

 which

1.21

 dlatego

1.14

 régulière

1.13

According

1.10

Indeed

1.09

Like

1.08

которы

1.07

 totiž

1.03

Activations Density 0.102%