INDEX

Explanations

elements related to social media events or controversies

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

å¤¢

-0.07

Ø·Ùģ

-0.06

æĵį

-0.06

 Sheriff

-0.06

.nlm

-0.06

ÑĨÐµ

-0.06

ieder

-0.06

ãĥ¬ãĤ¹

-0.06

à¤ªà¤°

-0.06

uckets

-0.06

POSITIVE LOGITS

 Hanna

0.06

ihan

0.06

ahan

0.06

gger

0.06

chin

0.06

fit

0.06

 Sawyer

0.06

Page

0.06

 sort

0.06

anager

0.05

Activations Density 0.004%