INDEX

Explanations

surnames followed by punctuation

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

 both

-1.63

both

-1.46

 bahkan

-1.39

 даже

-1.30

his

-1.30

 Both

-1.28

 sekä

-1.28

따

-1.25

to

-1.23

最后的

-1.23

POSITIVE LOGITS

if

2.13

who

1.36

();

1.33

 dzięki

1.33

entown

1.30

 který

1.30

 která

1.30

 предусмотрен

1.29

 detecta

1.29

:"

1.28

Activations Density 0.112%