INDEX

Explanations

away from or to someone

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

 disfraces

-1.42

 japones

-1.41

忡

-1.31

 sosis

-1.27

ПС

-1.26

 универ

-1.25

ticularly

-1.22

 chacune

-1.22

 två

-1.20

 thoſe

-1.19

POSITIVE LOGITS

on

1.61

zembro

1.36

in

1.30

as

1.30

 using

1.28

by

1.27

 where

1.26

 with

1.26

 into

1.21

 immediately

1.20

Activations Density 0.077%