INDEX

Explanations

bravery

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 brave

-1.22

 bravely

-1.16

brave

-1.12

 bravery

-1.06

 courage

-1.03

 coraggio

-0.95

 courageous

-0.93

Brave

-0.91

 valiente

-0.90

 Brave

-0.88

POSITIVE LOGITS

ly

0.79

ness

0.49

lust

0.47

 minds

0.47

ctor

0.47

LY

0.46

tor

0.46

ÉN

0.45

doe

0.44

 sort

0.44

Activations Density 1.572%