INDEX

Explanations

Quantity

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

rawid

-0.27

cat

-0.27

 cats

-0.25

ë¶Ħ

-0.25

ours

-0.24

åı¦ä¸Ģç§į

-0.24

Aut

-0.24

éķ¿èĢģ

-0.23

ipa

-0.23

pectrum

-0.23

POSITIVE LOGITS

åĪ¶çº¦

0.28

imming

0.28

äº§èĥ½

0.27

 fatt

0.26

 setInput

0.25

.getInfo

0.25

æĬ¼

0.25

çªĿ

0.25

ums

0.25

 productivity

0.24

Activations Density 0.007%