INDEX

Explanations

historical figures or titles

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

 booster

-0.62

Hauptartikel

-0.60

iores

-0.52

 boosters

-0.51

setViewName

-0.47

Présentation

-0.47

luci

-0.47

-0.45

ures

-0.45

 surla

-0.44

POSITIVE LOGITS

 électron

0.60

Personendaten

0.57

 étoient

0.57

 avoient

0.57

 étoit

0.56

CodedInputStream

0.53

bev

0.51

 auroit

0.51

 Zent

0.50

 pngtree

0.50

Activations Density 0.008%