INDEX

Explanations

thanks to everyone

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

 only

-1.30

𝚒

-1.16

 when

-1.11

 major

-1.07

 essendo

-1.05

iramente

-1.00

重大

-0.99

可

-0.96

田市

-0.96

menor

-0.94

POSITIVE LOGITS

who

1.69

 contributed

1.34

 dzisiaj

1.17

 involved

1.15

 которые

1.11

 those

1.07

 wszystkich

1.06

 "]";

1.05

 dziś

1.04

especially

1.03

Activations Density 0.021%