INDEX

Explanations

distribution throughout or across

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

 after

-1.05

 when

-1.01

 zawsze

-1.00

or

-0.99

 always

-0.98

 before

-0.97

when

-0.96

ريكي

-0.95

 při

-0.95

 endless

-0.94

POSITIVE LOGITS

 throughout

7.13

throughout

5.50

 Throughout

4.72

Throughout

4.72

 THRO

3.50

 khắp

2.70

 всю

2.52

 across

2.52

THRO

2.36

整个

2.28

Activations Density 0.311%