INDEX

Explanations

instances of collaboration and contributions to publications

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

ysz

-0.07

afort

-0.07

adro

-0.07

anya

-0.07

empo

-0.07

agen

-0.07

adena

-0.06

amax

-0.06

kus

-0.06

olet

-0.06

POSITIVE LOGITS

eline

0.06

 Contr

0.06

NAS

0.06

contr

0.06

zik

0.06

 Cheng

0.06

 widely

0.05

iou

0.05

-or

0.05

unning

0.05

Activations Density 0.005%