INDEX

Explanations

Happy holiday greetings

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

its

-0.95

speak

-0.94

 suyo

-0.90

淋

-0.90

swire

-0.89

 célèbre

-0.89

 убий

-0.89

 acción

-0.88

就要

-0.88

 WHILE

-0.87

POSITIVE LOGITS

to

1.21

Almost

1.02

Nearly

1.01

 Almost

0.95

 trails

0.92

 travels

0.91

Happy

0.90

 Họ

0.87

ございました

0.86

 early

0.85

Activations Density 0.004%