INDEX

Explanations

references to the word "Get," indicating the neuron is looking for instances of the word or command "Get" in 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

Efq

-0.94

Eſ

-0.90

 Monfieur

-0.89

 ſta

-0.86

 myſelf

-0.84

 raiſ

-0.84

 ſte

-0.83

 deſt

-0.83

 Reſ

-0.82

tagHelperRunner

-0.82

POSITIVE LOGITS

Get

1.03

GET

0.82

Ge

0.63

WebVitals

0.62

Koordinaten

0.58

ையில்

0.52

Ge

0.50

 '\\;'

0.48

ancienne

0.47

 presa

0.46

Activations Density 0.003%