INDEX

Explanations

mathematical proofs

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

æ¯Ķè¾ĥå¥½

-0.30

RANDOM

-0.28

æĺ¾

-0.27

ä¹Łå¥½

-0.27

æ¯ıä¸Ģ

-0.25

å¾Īå¥½

-0.25

åıī

-0.25

iei

-0.24

ÄĻp

-0.24

å·Ŀ

-0.24

POSITIVE LOGITS

 integer

0.30

nett

0.29

anel

0.28

çĭ¡

0.27

åĩºè·¯

0.26

xm

0.26

à¸Īà¸Ļ

0.25

 Jerseys

0.24

æİ§èĤ¡éĽĨåĽ¢

0.24

rub

0.24

Activations Density 0.893%