INDEX

Explanations

filled with

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 learnt

-0.25

 banner

-0.23

æ³ķä»¤

-0.23

rael

-0.23

æ¿ĢçĥĪçļĦ

-0.22

 Ibid

-0.22

æĢ»éĿ¢ç§¯

-0.22

 Ð¿ÑĢÐ¾Ð²ÐµÐ´ÐµÐ½Ð¸Ñı

-0.21

 Cree

-0.21

é²²

-0.21

POSITIVE LOGITS

æ»¡æ»¡çļĦ

0.44

æ»¡æ»¡

0.43

æ»¡äºĨ

0.40

 refill

0.38

å¡«åħħ

0.35

æ»¿

0.34

filled

0.33

åħħå®ŀ

0.32

 filled

0.32

 contents

0.30

Activations Density 0.040%