INDEX

Explanations

Comparisons and statistics

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

è²Į

-0.27

cratch

-0.26

pects

-0.25

ularity

-0.25

otate

-0.25

 circumstances

-0.25

ysize

-0.25

 operative

-0.25

łĢ

-0.24

äºĭæĥħ

-0.24

POSITIVE LOGITS

's

0.38

éĹ´çļĦ

0.35

çļĦ

0.34

ä¹ĭåīįçļĦ

0.33

çī¹æľīçļĦ

0.33

æľ¬èº«çļĦ

0.32

æıĲåĩºçļĦ

0.32

è¿ĻéĩĮçļĦ

0.32

çļĦå¤§

0.31

ä½¿çĶ¨çļĦ

0.30

Activations Density 0.014%