INDEX

Explanations

the phrase "positron emission tomography"

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Alike

-0.68

 Williamsburg

-0.67

 préfé

-0.66

 Devonian

-0.66

 aceptas

-0.64

 Cabello

-0.64

 gouver

-0.63

 autonome

-0.63

 africains

-0.62

 Jogos

-0.61

POSITIVE LOGITS

 positron

1.91

itron

1.43

 posit

1.05

posit

0.94

Pos

0.68

zyl

0.67

 Whitfield

0.65

rsiniz

0.65

 Griff

0.61

phens

0.61

Activations Density 0.001%