INDEX

Explanations

phrases associated with trying new things or 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

VEL

-0.07

ged

-0.06

oven

-0.06

pie

-0.06

 Merc

-0.06

ardy

-0.06

resi

-0.06

CESS

-0.06

ales

-0.06

rames

-0.06

POSITIVE LOGITS

out

0.07

oop

0.07

outil

0.06

TPL

0.06

 Fortune

0.06

 divert

0.06

fort

0.06

zip

0.06

asename

0.06

Ð¾ÑģÐ¿

0.06

Activations Density 0.010%