INDEX

Explanations

TLDR, headers, computed, coordinates

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

 When

-2.09

 když

-2.05

 cuando

-2.03

 όταν

-1.90

 ketika

-1.85

 quando

-1.85

 när

-1.83

 This

-1.82

-1.77

整体

-1.72

POSITIVE LOGITS

媖

2.14

 auffi

2.13

嫪

1.94

齜

1.87

髕

1.87

 zoude

1.84

 Monfieur

1.73

 AVEC

1.73

亊

1.73

 westfalen

1.71

Activations Density 0.004%