INDEX

Explanations

code syntax

code

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

Efq

-0.90

 ſeveral

-0.79

 onPostExecute

-0.77

 Cuban

-0.75

 itſelf

-0.75

 Monfieur

-0.72

 ſever

-0.71

 myſelf

-0.71

ſelf

-0.71

 Theſe

-0.71

POSITIVE LOGITS

intahan

0.46

 nueces

0.46

op

0.45

ver

0.44

seattle

0.43

Op

0.42

Ph

0.40

0.39

 makl

0.39

ph

0.39

Activations Density 1.427%