INDEX

Explanations

punctuation

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

è¿ĻçĤ¹

-0.34

chants

-0.28

è¿Ļä¸ĢçĤ¹

-0.27

COMP

-0.27

è±¸

-0.25

ewriter

-0.25

EVP

-0.25

iVar

-0.24

ULE

-0.24

ä¸ĢæĹ¦

-0.23

POSITIVE LOGITS

å®ĥ

0.38

it

0.34

It

0.32

cloak

0.30

æ¯ĶåĪ©

0.29

å¹½

0.28

æĽ´å¥½

0.27

It

0.26

å®ĥæĺ¯

0.26

—it

0.25

Activations Density 0.005%