INDEX

Explanations

comparisons and extremes

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

はもちろん

-1.52

 入荷

-1.34

为例

-1.28

 tehn

-1.27

 può

-1.27

と書

-1.23

 encor

-1.22

 MATTERS

-1.20

 hâte

-1.20

 美丽

-1.20

POSITIVE LOGITS

we

1.62

 that

1.38

 when

1.36

不会

1.34

1.19

 allow

1.16

 manera

1.16

 высоким

1.14

glą

1.13

 additional

1.12

Activations Density 0.279%