INDEX

Explanations

numerical references or structured metadata in the text

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

çļĦäºĭ

-0.07

rieben

-0.06

ÑĢÐ¾Ð²ÐµÑĢ

-0.06

etak

-0.06

trinsic

-0.06

rix

-0.06

ilan

-0.06

ritable

-0.06

 Constitution

-0.06

inate

-0.06

POSITIVE LOGITS

zon

0.08

yon

0.06

Ð»Ð¸ÐºÐ°

0.06

jon

0.06

enu

0.06

Aid

0.06

upa

0.06

Isl

0.06

Ð²ÑĢÐ¾Ð¿

0.06

KeyValue

0.06

Activations Density 0.001%