INDEX

Explanations

reported or self-reported

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 desempenho

-0.78

jast

-0.73

legd

-0.72

мото

-0.68

 Украине

-0.68

زینه

-0.68

اوى

-0.66

〉

-0.66

IOLOGY

-0.66

empel

-0.66

POSITIVE LOGITS

 reported

6.91

 report

6.44

 reports

6.31

 reporting

5.75

report

5.38

reported

5.22

 REPORT

5.09

Report

5.06

reports

5.00

Reported

4.97

Activations Density 0.424%