INDEX

Explanations

desired state or past occurrence

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

is

-2.22

are

-1.95

ствуют

-1.45

 છે

-1.45

美味しいです

-1.38

 हैं

-1.35

 kwamba

-1.30

 estão

-1.28

зывают

-1.20

 will

-1.20

POSITIVE LOGITS

was

5.50

 were

3.53

had

3.17

 وكان

3.13

 было

3.08

 была

2.91

 było

2.80

 était

2.78

 ήταν

2.75

 был

2.58

Activations Density 0.007%