INDEX

Explanations

if you

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

may

-1.35

might

-1.30

 pueden

-1.26

 может

-1.20

Might

-1.18

 probablemente

-1.16

prender

-1.13

 puede

-1.10

 peuvent

-1.09

 bahkan

-1.07

POSITIVE LOGITS

 want

1.76

 already

1.64

 find

1.47

 đang

1.43

are

1.38

 decide

1.26

 frequently

1.23

正在

1.19

还没有

1.16

กำลัง

1.16

Activations Density 0.044%