INDEX

Explanations

the phrase "full disclosure" and its variations in various contexts

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

desk

-0.07

imer

-0.07

andler

-0.07

-0.06

amb

-0.06

uur

-0.06

ugar

-0.06

odb

-0.06

assigned

-0.06

uc

-0.06

POSITIVE LOGITS

 full

0.12

/full

0.10

full

0.10

(full

0.10

 Full

0.10

 FULL

0.09

-full

0.09

Full

0.09

.full

0.09

FULL

0.08

Activations Density 0.018%