INDEX

Explanations

"The" followed by a specific noun

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits



-1.86

 других

-1.83

傒

-1.80

 nové

-1.73

 ſol

-1.72

齪

-1.70

 consulte

-1.64

 ſou

-1.62

 určit

-1.59

 BECAUSE

-1.53

POSITIVE LOGITS

 from

2.42

2.11

and

2.09

 there

1.93

 with

1.73

 Those

1.66

Those

1.66

 designated

1.57

 There

1.52

 while

1.51

Activations Density 0.049%

No Known Activations