INDEX

Explanations

noise reduction filtering

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Workout

-0.83

 Deferred

-0.75

 glucos

-0.74

ازات

-0.73

운

-0.72

 Franklin

-0.72

 Drill

-0.71

 disobedience

-0.71

心配

-0.70

曲が

-0.70

POSITIVE LOGITS

 noise

3.08

 Noise

2.55

noise

2.52

Noise

2.45

 NOISE

1.91

 noises

1.69

 noisy

1.65

 шу

1.48

 filtering

1.45

noisy

1.44

Activations Density 0.057%