INDEX

Explanations

changelog entries and descriptions

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Ши

2.68

Ч

2.64

 Чи

2.59

 Са

2.55

 Ди

2.54

 Ча

2.48

 Та

2.43

 Ти

2.40

 роз

2.39

МИ

2.38

POSITIVE LOGITS

 veden

1.65

 Anders

1.64

 sorgen

1.57

 anders

1.56

 problemen

1.47

 allerlei

1.46

 alles

1.46

 viel

1.46

ungen

1.46

 inner

1.44

Activations Density 0.033%