INDEX

Explanations

specific characters or symbols that may indicate errors or unusual items 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

Ð¾Ð´Ñĭ

-0.07

ckett

-0.06

Ben

-0.06

à¥ĩà¤¯à¤°

-0.06

airo

-0.06

cdb

-0.06

odge

-0.06

 beads

-0.06

urgeon

-0.06

hausen

-0.06

POSITIVE LOGITS

bal

0.18

BAL

0.12

bal

0.12

ted

0.12

-bal

0.11

Ø¨Ø§ÙĦ

0.10

abal

0.10

ub

0.10

dam

0.09

ball

0.09

Activations Density 0.003%