INDEX

Explanations

let alone or much less

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

 också

-0.94

也有

-0.91

 również

-0.88

maybe

-0.87

 använder

-0.84

やっぱり

-0.84

 именно

-0.83

 zarówno

-0.82

 vẫn

-0.82

 pól

-0.80

POSITIVE LOGITS

 much

4.72

let

3.52

much

3.19

Much

2.95

 Much

2.84

let

2.33

 apalagi

2.16

 MUCH

2.09

まして

1.95

 least

1.69

Activations Density 0.048%