INDEX

Explanations

technical string directive

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

が

-1.33

 maksimal

-1.33

 anglès

-1.29

-1.27

 dollari

-1.21

 konserv

-1.18

<>

-1.18

 teneur

-1.15

 enne

-1.14

 -->>

-1.14

POSITIVE LOGITS

 行っ

1.26

()]

1.25

ঐ

1.23

 який

1.21

鸰

1.18

 später

1.16

erkek

1.13

無し

1.11

 וכן

1.10

 рішення

1.10

Activations Density 0.064%