INDEX

Explanations

references to a specific individual's name within the text

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

 dAtA

-0.76

'&:

-0.76

AddTagHelper

-0.70

+#+#

-0.68

 Paglinawan

-0.68

ChildScrollView

-0.68

ISupport

-0.67

 Mercan

-0.67

WriteTagHelper

-0.67

tagHelperRunner

-0.67

POSITIVE LOGITS

describe

1.26

 Gardner

1.19

Gardner

1.07

Describe

1.02

 Baxter

0.96

POV

0.79

axter

0.75

pov

0.66

 Townsend

0.64

pov

0.60

Activations Density 0.009%