INDEX

Explanations

terms related to mathematical or statistical constructs, particularly involving equations or variables

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

 delightful

-0.08

.qq

-0.07

 delighted

-0.06

 performan

-0.06

 Ballet

-0.06

 delights

-0.06

subpackage

-0.06

 tarif

-0.06

 lovely

-0.06

 danced

-0.06

POSITIVE LOGITS

 fuck

0.13

 fucking

0.13

 fucked

0.12

 Fuck

0.12

fuck

0.11

 FUCK

0.11

 fucks

0.10

 Kill

0.10

Fuck

0.10

 shit

0.10

Activations Density 0.003%