INDEX

Explanations

repeated punctuation ending sentences

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

-2.55

-1.95

providedIn

-1.75

㈯

-1.72

 совершенно

-1.72

And

-1.71

盖

-1.71

Soon

-1.69

ra

-1.68

 respective

-1.67

POSITIVE LOGITS

 según

2.08

 algunos

1.91

 algunas

1.82

鐃

1.76

してました

1.74

 cette

1.73

 This

1.73

 says

1.72

 conocidas

1.69

 algún

1.66

Activations Density 0.006%