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

omial

-0.27

ious

-0.26

rouw

-0.25

iosity

-0.25

veau

-0.25

atters

-0.24

 layouts

-0.24

à¹Ĥà¸Ĺà¸£

-0.24

omp

-0.23

haps

-0.23

POSITIVE LOGITS

çļĦéĢŁåº¦

0.28

 catastrophe

0.26

graf

0.26

åºĶçĶ¨äºİ

0.25

ä¹ĹãĤĬ

0.25

_OT

0.24

èĴĤ

0.23

'&

0.23

gra

0.23

çļĦæĸ¹åĲĳ

0.23

Activations Density 0.001%

No Known Activations

This feature has no known activations.