INDEX

Explanations

names of actors

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

 both

-1.66

 that

-1.65

 publicó

-1.36

 lanzó

-1.30

 angefangen

-1.28

 many

-1.26

 everyone

-1.21

-1.20

 zarówno

-1.20

on

-1.19

POSITIVE LOGITS

isations

1.29

 ultimi

1.28

rebbe

1.25

 spion

1.20

 stessi

1.20

тисти

1.16

rebbero

1.16

 menyen

1.16

勝手に

1.15

 laga

1.14

Activations Density 0.052%