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

ç³Ĭæ¶Ĥ

-0.31

 coincidence

-0.26

 similarity

-0.25

 coinc

-0.25

UPC

-0.24

 mutual

-0.24

 decrypt

-0.24

loyd

-0.24

 joint

-0.23

 Mutual

-0.23

POSITIVE LOGITS

thon

0.31

Ð²Ð¸

0.28

gan

0.27

mith

0.26

rary

0.25

åĩ»è´¥

0.24

qli

0.24

ÙĤØ§ØªÙĦ

0.24

Ļ¨

0.24

 Vict

0.24

Activations Density 0.002%

No Known Activations

This feature has no known activations.