INDEX

Explanations

code

names of authors or researchers with unusual capitalization

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

Negative Logits

 PeEnEo

-0.51

pois

-0.51

ipal

-0.50

UserScript

-0.49

[]:

-0.49

CPtr

-0.49

usehen

-0.48

COUVER

-0.47

 AtomicInteger

-0.47

/?

-0.47

POSITIVE LOGITS

 perfons

0.61

PerformLayout

0.55

quelize

0.53

DeleteBehavior

0.51

 >=",

0.50

ItemLayout

0.49

ActionCreators

0.47

 fhort

0.45

charAt

0.44

Numerology

0.44

Activations Density 1.032%