INDEX

Explanations

discussions about social constructs and relationships

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

ially

-0.07

EMPLARY

-0.07

à¹Ģà¸Ńà¸ĩ

-0.06

/doc

-0.06

edelta

-0.06

ares

-0.06

¦¬

-0.06

col

-0.06

flt

-0.06

estre

-0.06

POSITIVE LOGITS

igger

0.06

chy

0.06

 NÄĽm

0.06

nelle

0.06

 Tome

0.06

/&

0.06

abi

0.06

 Sommer

0.06

ANGE

0.05

Activations Density 0.033%