INDEX

Explanations

No Explanations Found

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

imizer

-0.28

Ã³w

-0.27

MBER

-0.27

zy

-0.25

åĵģ

-0.24

 uneasy

-0.24

 chic

-0.23

zw

-0.23

ymb

-0.23

æĢ¨

-0.23

POSITIVE LOGITS

åħ¬åı¸å°Ĩ

0.29

gran

0.28

azen

0.27

å®¢æĪ·æıĲä¾Ľ

0.26

éĻįä½İæĪĲæľ¬

0.26

eah

0.26

getter

0.25

uria

0.25

 Wand

0.24

å®¢æĪ·éľĢæ±Ĥ

0.24

Activations Density 0.001%

No Known Activations

This feature has no known activations.