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

Eb

-0.28

_linux

-0.26

oi

-0.25

 honour

-0.25

 complying

-0.24

 obedience

-0.24

FileSync

-0.24

 nÃ¤mlich

-0.24

åģļçļĦ

-0.23

.gstatic

-0.23

POSITIVE LOGITS

 Stap

0.28

Gap

0.28

-gap

0.27

este

0.26

onte

0.25

pras

0.24

nee

0.24

 Chern

0.24

å»¶ä¼¸

0.24

ç«£

0.24

Activations Density 0.059%

No Known Activations

This feature has no known activations.