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

urv

-0.29

èĲ½

-0.28

vecs

-0.28

èĭ·

-0.27

impl

-0.27

ottom

-0.27

 Crane

-0.26

çĶļèĩ³æĺ¯

-0.25

LEV

-0.24

na

-0.24

POSITIVE LOGITS

DebugEnabled

0.30

eworthy

0.26

ack

0.25

iciency

0.25

èļĮ

0.25

å·´åŁº

0.25

inely

0.24

ascus

0.24

.pk

0.24

(express

0.23

Activations Density 0.883%

No Known Activations

This feature has no known activations.