INDEX

Explanations

references to terrorist classifications and related groups

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

acid

-0.06

arÄ±m

-0.06

Ub

-0.06

.Null

-0.06

orce

-0.06

contri

-0.06

ulous

-0.06

 Dwight

-0.06

ritable

-0.06

eroon

-0.06

POSITIVE LOGITS

 designation

0.12

 designated

0.12

 listing

0.11

 listed

0.11

 listings

0.10

 terrorist

0.10

listing

0.10

-list

0.09

 pros

0.09

designation

0.09

Activations Density 0.011%