INDEX

Explanations

first, number, letter sequence

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

 trenger

-1.21

第二个

-1.13

 第二

-1.13

鏖

-1.05

第二

-1.04

Those

-1.03

Usually

-1.03

Beskrivning

-1.02

Often

-1.01

なんですね

-1.01

POSITIVE LOGITS

۱

1.16

 first

1.16

 första

1.12

１

1.05

 eerste

1.04

১

1.01

 первого

1.00

১

0.98

หนึ่ง

0.98

 sämtliche

0.96

Activations Density 0.019%