INDEX

Explanations

references to the concept of joining or connecting

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

joined

-0.84

joint

-0.75

 joined

-0.74

 joint

-0.74

 Joined

-0.68

 joints

-0.68

 BorderRadius

-0.68

 jointly

-0.66

multirow

-0.65

contentLoaded

-0.64

POSITIVE LOGITS

Join

1.07

 Join

0.98

 join

0.80

AddTagHelper

0.73

+#+

0.60

 exposição

0.57

 demolished

0.56

 mueble

0.54

 disparu

0.54

 mourut

0.54

Activations Density 0.004%