INDEX

Explanations

German language and politeness

New Auto-Interp

Configuration

Prompts (Dashboard)

238,145 prompts, 512 tokens each

Dataset (Dashboard)

lmsys + oasst1

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 staring

1.59

 ১০

1.55

 traditionally

1.55

 conflicting

1.50

 typically

1.47

 most

1.46

 arguably

1.45

 commonly

1.44

 frantic

1.43

 incredibly

1.40

POSITIVE LOGITS

auf

2.30

 selbst

2.22

 nach

2.20

 durch

2.16

 für

2.14

 aufgrund

2.13

 nicht

2.08

 bereits

2.07

 verschiedene

2.05

 zwischen

2.04

Activations Density 0.129%