the verb "to be" in various forms and 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

undra

-0.07

ammad

-0.07

ailer

-0.07

ÏĢÏĮ

-0.07

iless

-0.07

æŁı

-0.07

inkle

-0.07

enus

-0.07

ettle

-0.06

uels

-0.06

POSITIVE LOGITS

 that

0.08

an

0.07

avia

0.06

phin

0.06

 something

0.06

 increased

0.06

 bahwa

0.06

Activations Density 0.006%