INDEX

Explanations

light

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

 Light

-0.69

 light

-0.68

 LIGHT

-0.58

Light

-0.55

]+"

-0.47

 vore

-0.47

 licht

-0.46

 externi

-0.46

light

-0.45

 &___

-0.45

POSITIVE LOGITS

IntoConstraints

0.94

 pinulongan

0.66

 nahilalakip

0.58

getWriter

0.57

waves

0.54

 dosage

0.54

StreamReader

0.54

PMailer

0.54

bath

0.53

setopt

0.53

Activations Density 0.072%