INDEX

Explanations

phrases related to ease and simplicity in processes or experiences

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

mad

-0.06

bum

-0.06

mad

-0.06

 developed

-0.06

ans

-0.06

im

-0.05

etc

-0.05

 Needle

-0.05

;base

-0.05

 involved

-0.05

POSITIVE LOGITS

achel

0.08

ktop

0.07

.ali

0.07

remen

0.07

Invoker

0.07

amins

0.07

hci

0.07

anches

0.07

yat

0.07

Activations Density 0.032%