INDEX

Explanations

testing

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

monger

-0.82

fera

-0.79

 اح

-0.79

 cuna

-0.75

Pinterest

-0.71

𝒜

-0.69

гії

-0.69

 pendidikan

-0.67

pinterest

-0.67

 Handbuch

-0.67

POSITIVE LOGITS

 testing

3.59

 Testing

2.70

 tests

2.64

 test

2.56

Testing

2.52

 tested

2.27

testing

2.22

 TESTING

2.11

 Test

2.02

 Tests

2.00

Activations Density 0.011%