INDEX

Explanations

references to weight, heaviness, or laziness

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

 Johns

-0.06

kek

-0.06

unde

-0.06

ROWS

-0.06

 ansch

-0.06

ustos

-0.06

 Harr

-0.05

ROW

-0.05

ruz

-0.05

BarButton

-0.05

POSITIVE LOGITS

ily

0.17

iness

0.16

ier

0.12

ying

0.12

ystate

0.12

ystone

0.11

iosity

0.11

(il

0.11

ych

0.11

ymax

0.11

Activations Density 0.008%