INDEX

Explanations

phrases emphasizing quantity or degree, particularly the use of the word "quite" or variations of "a"

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

 very

-0.06

 somewhat

-0.06

qv

-0.06

mer

-0.06

 kinds

-0.06

ruc

-0.06

ase

-0.06

 only

-0.06

 Bulk

-0.05

ç§į

-0.05

POSITIVE LOGITS

-ÑĤÐ°ÐºÐ¸

0.10

 amount

0.08

LBL

0.07

amount

0.07

DownList

0.07

Ð²Ð°Ð¹

0.07

oker

0.07

 ÑģÐµÐ±Ðµ

0.07

ude

0.07

atta

0.07

Activations Density 0.004%