INDEX

Explanations

references to mechanisms or objects that are physically moved or displaced

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

 Knock

-0.78

Knock

-0.72

 touch

-0.69

 Knockout

-0.67

 Touch

-0.62

knock

-0.61

 TOUCH

-0.60

 knockdown

-0.60

 smooth

-0.57

Touch

-0.56

POSITIVE LOGITS

 knocked

2.08

 knocking

1.22

 knocks

1.15

Kno

1.11

Kno

0.82

kno

0.78

 referenties

0.77

elemField

0.72

 nahilalakip

0.61

Diwedd

0.60

Activations Density 0.001%