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

 squeeze

-0.29

ç«Ļéķ¿

-0.27

 ÃŃndice

-0.26

 yÃªn

-0.26

æĮ¹

-0.26

edx

-0.25

tie

-0.25

 bench

-0.24

 span

-0.24

 groom

-0.24

POSITIVE LOGITS

é¸¿

0.28

HF

0.26

ijkstra

0.26

ITU

0.25

å¼ºçĥĪ

0.25

ç£·éħ¸

0.25

ificant

0.25

BF

0.24

å·®å¼Ĥ

0.24

èĤĭ

0.24

Activations Density 0.005%

No Known Activations

This feature has no known activations.