INDEX

Explanations

Long, unstructured texts

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

 immensely

-0.27

Ð·Ð¾Ð²

-0.26

å¾Īå¤ļ

-0.26

å¾Īå¤ļäºĭæĥħ

-0.25

Ð°Ð»Ð¸Ð·

-0.25

èİ¹

-0.25

ifers

-0.25

Ð¾Ð²Ð¸Ñĩ

-0.24

liest

-0.24

iest

-0.24

POSITIVE LOGITS

æĢ»æĶ¶åħ¥

0.31

çĶŁäº§åĴĮ

0.31

çĶŁäº§

0.28

åįĬ

0.26

DataExchange

0.26

çĶŁäº§å·¥èīº

0.26

 :↵

0.25

çĶŁçĶ¢

0.24

 contemplated

0.24

>Date

0.24

Activations Density 0.003%