INDEX

Explanations

developing methods for

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

彼らは

-1.47

 determinados

-1.44

骉

-1.40

 provenientes

-1.38

 oferec

-1.37

 proveniente

-1.35

 wykonane

-1.34

-1.30

 многих

-1.29

POSITIVE LOGITS

for

3.58

to

2.47

 that

1.87

and

1.84

 about

1.61

 because

1.56

who

1.51

 possible

1.38

 which

1.38

 with

1.36

Activations Density 0.174%