INDEX

Explanations

German numbers, suffixes, endings

LMSYS

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

heni

0.42

>&

0.40

yr

0.40

ూర్

0.39

oun

0.38

usk

0.38

aurant

0.38

hen

0.37

}-

0.36

 Sunt

0.36

POSITIVE LOGITS

ierend

0.52

 entsprechend

0.48

 vielleicht

0.47

izieren

0.46

 sicher

0.46

ifizierung

0.46

istisch

0.45

CHREIBUNG

0.45

 jahr

0.45

isiert

0.45

Activations Density 0.007%