INDEX

Explanations

expressions of authenticity and sincerity in relationships and experiences

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

.au

-0.09

utron

-0.06

angan

-0.06

UZ

-0.06

ÑĢÐµÐ¼Ñı

-0.06

borough

-0.06

æķ¦

-0.06

stras

-0.06

 Hats

-0.06

isco

-0.06

POSITIVE LOGITS

 truly

0.09

 Truly

0.08

meaning

0.07

æĦıä¹ī

0.07

ÑĥÐ³

0.07

/false

0.07

ppo

0.07

iy

0.07

çľŁæŃ£

0.06

 meaning

0.06

Activations Density 0.018%