INDEX

Explanations

archival research and data

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

蛧

-2.30

 plupart

-2.05

}{

-2.02

);

-1.98

㉗

-1.94

 նաև

-1.90

sukienka

-1.88

鏷

-1.88

ється

-1.88

</h5>

-1.88

POSITIVE LOGITS

This

2.34

ه

2.19

(^^

2.13

 enrique

1.99

場に

1.98

 lamenta

1.95

 Juegos

1.93

 reiv

1.92

ݯ

1.89

 fala

1.88

Activations Density 0.013%