INDEX

Explanations

references to the Earth and its scientific or physical characteristics

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

adera

-0.07

udad

-0.07

arget

-0.07

à¸ªà¸ģ

-0.07

bersome

-0.07

stalk

-0.07

fony

-0.06

croft

-0.06

UTDOWN

-0.06

lech

-0.06

POSITIVE LOGITS

 Flat

0.19

 flat

0.18

Flat

0.17

-flat

0.14

flat

0.14

 flatt

0.13

 spherical

0.13

 flattened

0.12

 flatten

0.12

_flat

0.11

Activations Density 0.007%