INDEX

Explanations

Author et al. citations

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

and

-1.72

 with

-1.70

 includes

-1.52

 including

-1.48

包括

-1.47

You

-1.45

-1.41

３

-1.40

 включает

-1.40

had

-1.40

POSITIVE LOGITS

 muualla

1.71

 semblent

1.65

 pourraient

1.51

 mineures

1.50

 italien

1.37

 hulle

1.35

 diğer

1.30

 inspiré

1.30

 lyst

1.26

 Sistemas

1.25

Activations Density 0.097%