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

edList

-0.28

did

-0.27

 Cone

-0.26

bat

-0.25

ãģŀ

-0.25

 Pert

-0.25

çī¹æľĹ

-0.24

 Parts

-0.24

Tul

-0.24

POSITIVE LOGITS

å¿ĺ

0.29

 verz

0.27

ç©·

0.26

Dig

0.25

 sacrific

0.24

ä½ĨçĶ±äºİ

0.24

æ¹Ľ

0.24

æ´¾

0.24

ç»ĵåĲĪèµ·æĿ¥

0.24

 deception

0.24

Activations Density 0.001%

No Known Activations

This feature has no known activations.