INDEX

Explanations

dictionary/object access and table views

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

 estekak

-2.28

琑

-2.22

cedent

-2.17

螄

-2.11

něž

-2.08

 ciebie

-2.03

渕

-1.96

/>;

-1.94

anganronpa

-1.94

fördert

-1.93

POSITIVE LOGITS

3.28

2.73

↵

2.69

大概是

2.66

2.58

2.53

 murky

2.38

2.28

 weary

2.23

2.19

Activations Density 0.001%