INDEX

Explanations

word followed by of or to

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

-1.54

 these

-1.34

 those

-1.30

 their

-1.20

 that

-1.13

 estremamente

-1.09

our

-1.05

 Gegenstand

-0.99

 Besitzer

-0.98

 certain

-0.97

POSITIVE LOGITS

the

3.13

 ofthe

2.22

OfThe

2.16

ofthe

1.77

InThe

1.51

˃

1.25

The

1.22

tothe

1.20

⭐⭐⭐⭐

1.16

fort

1.15

Activations Density 0.191%