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

ãĥĲãĥ«

-0.26

 FORE

-0.25

ç®

-0.25

 attach

-0.25

elay

-0.25

kom

-0.24

 Ð¾Ð±ÑĢÐ°Ð·Ð¾Ð²Ð°Ð½Ð¸Ñı

-0.24

 váºŃt

-0.24

attach

-0.23

gag

-0.23

POSITIVE LOGITS

brains

0.31

terr

0.27

 Pepper

0.26

renom

0.26

dop

0.25

æ½¼

0.25

æ²Ķ

0.25

edic

0.25

mers

0.24

feit

0.24

Activations Density 0.003%

No Known Activations

This feature has no known activations.