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

 wykon

-0.26

 Studio

-0.26

pter

-0.26

}):

-0.25

Ð¸Ð»

-0.25

ifetime

-0.25

 Marian

-0.25

hoot

-0.24

 Garner

-0.24

illard

-0.24

POSITIVE LOGITS

ase

0.27

eor

0.25

ä½¿ä¹ĭ

0.25

resh

0.24

abric

0.23

 satisf

0.23

ond

0.23

èĩªæŁ¥

0.23

èģĶç½ĳ

0.23

æĴŃæĬ¥

0.23

Activations Density 0.074%

No Known Activations

This feature has no known activations.