INDEX

Explanations

references to geopolitical entities and conflicts involving Israel, Palestine, and surrounding nations

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

isay

-0.07

emm

-0.07

imple

-0.07

Ã©f

-0.07

atta

-0.07

loth

-0.06

asti

-0.06

Î·Î½

-0.06

krom

-0.06

oth

-0.06

POSITIVE LOGITS

 alike

0.09

 sides

0.06

ancy

0.06

istrov

0.06

alc

0.06

avery

0.06

opal

0.05

uele

0.05

.dds

0.05

cre

0.05

Activations Density 0.023%