INDEX

Explanations

articles referring to people or groups

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

elere

-0.08

borough

-0.08

OMEM

-0.07

ulan

-0.07

andez

-0.07

ellas

-0.07

esser

-0.07

 Ð½ÐµÐ´ÐµÐ»

-0.07

leston

-0.07

Ø³ØªØ±

-0.07

POSITIVE LOGITS

 someone

0.10

 person

0.10

 somebody

0.08

 individual

0.08

man

0.07

 member

0.07

someone

0.07

ActionCreators

0.06

 Alliance

0.06

 Someone

0.06

Activations Density 0.033%