INDEX

Explanations

gift packaging and presentation

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

 Zimmer

-0.87

牝

-0.86

xiang

-0.85

gación

-0.85

xit

-0.83

busch

-0.80

pting

-0.80

 ajan

-0.79

 краски

-0.77

 принципе

-0.77

POSITIVE LOGITS

 ribbon

1.31

 gift

1.25

 packaging

1.20

 presentation

1.13

 tied

1.11

 tissue

1.09

 cello

1.03

 Packaging

1.03

packaging

0.99

Presentation

0.98

Activations Density 0.017%