INDEX

Explanations

phrases indicating high performance and quality in engineering or product descriptions

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

enburg

-0.07

-0.06

igo

-0.06

 doomed

-0.06

postalcode

-0.06

YO

-0.06

LOSS

-0.05

 whose

-0.05

/L

-0.05

POSITIVE LOGITS

 performance

0.08

icari

0.07

unker

0.07

ablish

0.07

Ã©nom

0.07

ayi

0.07

.Apis

0.07

 economics

0.07

 overall

0.07

 performances

0.07

Activations Density 0.019%