INDEX

Explanations

punctuation marks and sentence endings within the text

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

allis

-0.07

RICT

-0.07

åħ

-0.07

postalcode

-0.07

èĩ³å°ĳ

-0.06

ÑıÑĩÐ¸

-0.06

abei

-0.06

geh

-0.06

ypad

-0.06

POSITIVE LOGITS

 thus

0.12

 thereby

0.11

 meaning

0.10

 therefore

0.10

 unlike

0.10

thus

0.09

 Thus

0.09

 Meaning

0.08

meaning

0.08

 hence

0.08

Activations Density 0.025%