INDEX

Explanations

questions that probe for understanding, curiosity, or concern about various topics

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

-fontawesome

-0.07

lier

-0.07

icer

-0.07

æ¢¯

-0.06

 antlr

-0.06

UTERS

-0.06

.poi

-0.06

 Ð³Ð¾ÑģÐ¿

-0.06

tsky

-0.06

edb

-0.06

POSITIVE LOGITS

0.06

ãĥķãĤ

0.06

udded

0.06

quam

0.05

ible

0.05

unction

0.05

 stuff

0.05

izoph

0.05

Ð¾ÑģÐºÐ¾Ð²

0.05

 CHtml

0.05

Activations Density 0.025%