INDEX

Explanations

numbers and items in lists

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

 this

-1.35

it

-1.18

 where

-1.15

or

-1.11

at

-1.08

侖

-1.07

 根据

-1.06

its

-1.05

any

-1.04

POSITIVE LOGITS

 morceaux

1.33

 pamoja

1.26

 ſont

1.22

 fufficient

1.20

 maniere

1.19

 två

1.14

我们

1.13

 pidió

1.13

 pelúcia

1.12

 τῆς

1.11

Activations Density 0.006%