INDEX

Explanations

writing to inform or explain

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

縢

-1.45

 barbati

-1.41

謦

-1.40

过来了

-1.36

ㇼ

-1.33

⬯

-1.32

weds

-1.30

轂

-1.28

 anello

-1.28

ppure

-1.28

POSITIVE LOGITS

 This

1.96

 because

1.91

 They

1.81

 These

1.69

 Their

1.63

for

1.59

Are

1.54

 Они

1.49

 they

1.42

 diğer

1.35

Activations Density 0.116%