INDEX

Explanations

references to alternative options or comparisons in various contexts

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

ãģ¾ãģ¾

-0.08

anner

-0.08

.grp

-0.08

ãĢįãĢĮ

-0.07

.TypeOf

-0.07

/Branch

-0.07

ÅŁk

-0.07

tera

-0.07

Äįas

-0.07

 âĢª

-0.07

POSITIVE LOGITS

 things

0.11

 thing

0.09

things

0.08

 others

0.08

 reasons

0.07

 cosas

0.07

thing

0.07

Things

0.07

 else

0.06

 ello

0.06

Activations Density 0.004%