INDEX

Explanations

words and phrases related to specific topics or contexts

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

riere

-0.08

Ari

-0.07

inator

-0.07

Ī¬

-0.07

ura

-0.07

ARA

-0.07

Ara

-0.07

Roy

-0.06

ARAM

-0.06

erer

-0.06

POSITIVE LOGITS

ernen

0.13

ern

0.13

erte

0.13

ernes

0.12

ernel

0.12

erti

0.12

erna

0.12

erten

0.12

ernal

0.12

ertz

0.12

Activations Density 0.041%