INDEX

Explanations

distinguishing between options

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

 jeweiligen

-1.71

We

-1.70

‘

-1.65

 даже

-1.61

?”

-1.59

 каждый

-1.57

 каждом

-1.55

-1.52

素敵

-1.50

 (‘

-1.49

POSITIVE LOGITS

2.13



2.02

曏

1.83

 joão

1.70

 étroite

1.68

 समीक्षाएं

1.66

 using

1.61

 peruan

1.59

.."

1.56

decoración

1.55

Activations Density 0.015%