INDEX

Explanations

No Explanations Found

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

adj

-0.06

hod

-0.06

acas

-0.06

ÃŃ

-0.05

 extingu

-0.05

 Hood

-0.05

asaki

-0.05

 Shirt

-0.05

 Borrow

-0.05

łí

-0.05

POSITIVE LOGITS

rax

0.08

exion

0.08

iego

0.08

abox

0.07

uest

0.07

otonin

0.07

mani

0.07

precated

0.07

NSBundle

0.07

/fw

0.07

Activations Density 0.000%

No Known Activations

This feature has no known activations.