INDEX

Explanations

discussions related to policies and their impact

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

lus

-0.08

ness

-0.07

ality

-0.06

errer

-0.06

orus

-0.06

ilis

-0.06

iao

-0.06

pard

-0.06

itia

-0.06

lot

-0.06

POSITIVE LOGITS

-makers

0.12

 makers

0.11

-maker

0.10

 maker

0.09

-policy

0.09

Maker

0.09

 Maker

0.09

makers

0.09

maker

0.08

/legal

0.08

Activations Density 0.012%