INDEX

Explanations

negative phrases or expressions

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

zcze

-0.09

arge

-0.07

Ã±

-0.07

nt

-0.07

SC

-0.07

hn

-0.06

TS

-0.06

aye

-0.06

ent

-0.06

POSITIVE LOGITS

 better

0.12

 such

0.10

 telling

0.09

 Ð»ÑĥÑĩÑĪÐµ

0.09

better

0.08

 Such

0.08

 Better

0.08

 harm

0.08

etten

0.08

 limit

0.08

Activations Density 0.011%