INDEX

Explanations

specific popular culture references and notable names

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

doch

-0.07

elda

-0.07

dd

-0.07

ATCH

-0.07

arna

-0.06

 Matter

-0.06

æ¬

-0.06

idot

-0.06

ys

-0.06

 Load

-0.06

POSITIVE LOGITS

 Compact

0.07

unting

0.07

xCD

0.06

Sci

0.06

Ķ

0.06

ambre

0.06

oler

0.06

EI

0.06

Activations Density 0.001%