INDEX

Explanations

mathematical expressions

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

蓠

-1.68

 enorme

-1.63

뻣

-1.52



-1.51

zemu

-1.48

螃

-1.45

hva

-1.44

ྵ

-1.38

wohner

-1.38

 Anda

-1.37

POSITIVE LOGITS

for

2.47

and

2.25

 when

1.59

 для

1.55

 after

1.53

,:)

1.41

 asegurarse

1.31

 ausdrück

1.29

 hacerle

1.27

สำหรับ

1.27

Activations Density 0.062%