INDEX

Explanations

terms and phrases related to military or national security contexts

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

↵

-0.10

-0.07

↵↵

-0.06

âĢ¦and

-0.06

:↵

-0.06

âĢ¦

-0.05

Ì£

-0.05

.diag

-0.05

POSITIVE LOGITS

 Everything

0.08

 Nothing

0.07

ENTE

0.07

Everything

0.07

vfs

0.07

everything

0.07

Seats

0.07

EVER

0.07

 NOTHING

0.07

tv

0.07

Activations Density 0.001%