INDEX

Explanations

languages and alphabets

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

SPEC

-0.28

éģĵ

-0.26

irl

-0.25

ä¸ªåŁİå¸Ĥ

-0.24

MAS

-0.24

èİ«æĸ¯

-0.24

 genom

-0.24

CRA

-0.23

èº«å¤Ħ

-0.23

ç¥ŀä»Ļ

-0.23

POSITIVE LOGITS

 known

0.28

ÂŃi

0.27

æľ¬ç«Ļ

0.26

.tel

0.25

known

0.25

TeV

0.25

æĭ¼éŁ³

0.25

 Known

0.24

ilater

0.24

ZW

0.24

Activations Density 0.890%