INDEX

Explanations

amp words and completions

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

桕

-3.13

 土産

-2.81

 撮り

-2.52

⸫

-2.52

 sabía

-2.34

 necesitaba

-2.33



-2.23

 todėl

-2.22

"}";

-2.22

 resultó

-2.22

POSITIVE LOGITS

3.98

3.41

3.02

ed

2.86

ндарт

2.80

唧

2.77

 sinister

2.75

橚

2.72

2.70

 wyłą

2.64

Activations Density 0.015%