INDEX

Explanations

parameters related to uncertainties in models or measurements

attends to mathematical terms and expressions from various technical tokens.

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

Negative Logits

_listener

-0.06

Ctrls

-0.06

Ð·Ð²

-0.06

ê·

-0.06

 Geographic

-0.05

 addCriterion

-0.05

CharCode

-0.05

ipar

-0.05

dispatch

-0.05

/hash

-0.05

POSITIVE LOGITS

 play

0.20

 Play

0.18

 playful

0.17

Play

0.17

play

0.16

 PLAY

0.16

-play

0.15

 games

0.15

_play

0.15

PLAY

0.14

Activations Density 0.012%