INDEX

Explanations

words found when talking about education, therapy, fights, and general back-and-forth dialogue

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

 referenties

-0.67

SequentialGroup

-0.66

 ExecuteAsync

-0.59

 ControllerBase

-0.58

StoryboardSegue

-0.58

 saites

-0.58

IContainer

-0.55

stdc

-0.54

IndentedString

-0.54

PhysRevLett

-0.54

POSITIVE LOGITS

 face

2.14

face

1.84

Face

1.73

 Face

1.63

 FACE

1.45

FACE

1.42

 faccia

1.20

 faces

1.15

faces

1.02

faced

0.93

Activations Density 7.593%