INDEX

Explanations

hacking

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

 hacks

-0.66

StoryboardSegue

-0.63

 Hacks

-0.60

 Hacker

-0.60

 hack

-0.57

ỡng

-0.56

 Herzog

-0.56

 Hound

-0.55

 Hack

-0.54

hack

-0.52

POSITIVE LOGITS

DockStyle

0.97

ValueStyle

0.81

bootstrapcdn

0.78

awtextra

0.69

RTEE

0.56

Juf

0.55

RegressionTest

0.54

WaitGroup

0.54

 facie

0.53

ViewInit

0.52

Activations Density 0.025%