INDEX

Explanations

example of a sequence or rule

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

we

-1.52

也是

-1.44

也

-1.37

 also

-1.36

也在

-1.34

-1.28

라는

-1.24

 також

-1.23

according

-1.23

 também

-1.20

POSITIVE LOGITS

for

1.59

 when

1.55

new

1.53

 bēr

1.41

 newly

1.32

 oggi

1.30

 tikai

1.30

 these

1.27

šo

1.27

 traditionally

1.26

Activations Density 0.951%