INDEX

Explanations

names followed by punctuation

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

↵↵↵↵↵↵↵↵↵↵↵↵

-0.92

↵↵↵↵↵↵↵↵↵↵↵

-0.90

↵↵↵↵↵↵↵↵↵↵↵↵↵

-0.86

↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵

-0.84

 identifiés

-0.81

krut

-0.81

יתוף

-0.79

 więc

-0.79

↵↵↵↵↵↵

-0.78

↵↵↵↵↵↵↵↵↵↵↵↵↵↵

-0.77

POSITIVE LOGITS

’

3.02

1.56

 Class

1.47

('

1.41

$('

1.31

['

1.30

 class

1.27

‘

1.22

Class

1.16

BA

1.14

Activations Density 0.021%