INDEX

Explanations

terms relating to data, personal versus public contexts, and modernity in discussions

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

lek

-0.07

klu

-0.07

geo

-0.07

Vs

-0.07

lessly

-0.06

ystone

-0.06

mul

-0.06

urr

-0.06

 beforeSend

-0.06

ÄįnÄĽ

-0.06

POSITIVE LOGITS

 alike

0.19

 worlds

0.10

 respectively

0.09

 sides

0.09

 Worlds

0.09

 modes

0.08

 equally

0.07

 respective

0.07

 olmak

0.07

 halves

0.07

Activations Density 0.040%