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

eurs

-0.28

ec

-0.28

èģĮæĿĥ

-0.28

lim

-0.26

_EC

-0.26

ucid

-0.25

ä¹±

-0.25

tt

-0.25

 terms

-0.25

us

-0.25

POSITIVE LOGITS

èĥĮä¸Ĭ

0.34

è·¯è¿ĩ

0.27

è¿ĩåī©

0.25

imonial

0.25

hani

0.25

è¹¶

0.25

/pg

0.25

èĥĮ

0.24

 dang

0.24

onation

0.24

Activations Density 0.007%

No Known Activations

This feature has no known activations.