INDEX

Explanations

sentence terminators and connectors

New Auto-Interp

Configuration

Prompts (Dashboard)

238,145 prompts, 512 tokens each

Dataset (Dashboard)

lmsys + oasst1

Embeds

IFrame

Link

Negative Logits

 therefore

1.55

 Therefore

1.52

Therefore

1.46

因此

1.42

 instead

1.38

 Instead

1.37

 quindi

1.33

therefore

1.32

 поэтому

1.28

 因此

1.27

POSITIVE LOGITS

 certainly

0.86

 banyak

0.84

 Certainly

0.83

Certainly

0.79

 although

0.78

 många

0.76

確かに

0.76

although

0.76

MANY

0.75

Depends

0.74

Activations Density 0.025%

No Known Activations