INDEX

Explanations

variations of the letter 'K' or words starting with 'K'

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

face

-0.07

éĿ¢

-0.07

 face

-0.06

vise

-0.06

Faces

-0.06

encil

-0.06

Ð°ÑĢÐ°Ð¼

-0.06

ì§Ŀ

-0.06

gren

-0.06

 burnt

-0.05

POSITIVE LOGITS

ãĥ¬ãĤ¹

0.07

dog

0.07

aber

0.07

uti

0.07

pec

0.07

alie

0.07

ëłĪìĬ¤

0.07

ooth

0.07

0.06

Activations Density 0.001%