INDEX

Explanations

the word "actor"

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

存于互联网档案馆

-0.95

CppMethod

-0.86

FormState

-0.79

titleMargin

-0.75

 createDate

-0.75

 nationaux

-0.73

 Pliny

-0.73

 varandra

-0.73

DSG

-0.73

 getRule

-0.73

POSITIVE LOGITS

 Actors

1.32

 actor

1.25

 Actor

1.20

Actors

1.18

 actors

1.17

Actor

1.09

actors

1.09

actor

1.05

ACTOR

1.05

 actress

0.87

Activations Density 0.005%