INDEX

Explanations

phrases that express evaluation or judgment, particularly regarding quality and effectiveness

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Embeds

IFrame

Link

Negative Logits

erli

-0.08

Ordered

-0.07

urga

-0.07

ako

-0.06

addir

-0.06

acaÄŁ

-0.06

Ø§Ø®

-0.06

SCI

-0.06

.mvp

-0.06

uml

-0.06

POSITIVE LOGITS

mes

0.07

wor

0.06

 card

0.06

/utility

0.06

ummings

0.06

 combo

0.06

 nicely

0.05

 Rarity

0.05

Ved

0.05

-placement

0.05

Activations Density 0.002%

No Known Activations