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

ãĥŃãĥ¼

-0.33

 YayÄ±n

-0.31

izada

-0.26

iales

-0.25

 *----------------------------------------------------------------

-0.25

uchar

-0.25

 synchronized

-0.25

ooter

-0.25

atile

-0.24

 promot

-0.24

POSITIVE LOGITS

ducted

0.27

phony

0.27

ventions

0.25

åŃķ

0.25

 Garn

0.25

è¨Ĺ

0.24

æĵ¦

0.24

unity

0.24

pla

0.24

eve

0.24

Activations Density 0.003%

No Known Activations

This feature has no known activations.