INDEX

Explanations

academic author surnames

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

Technologie

-1.72

ಝ

-1.71

راهن

-1.67

ಘ

-1.66

豊富な

-1.63



-1.51

筈

-1.47

نسي

-1.44

zdroj

-1.43

детская

-1.41

POSITIVE LOGITS

1.65

等人

1.58

は約

1.55

strokeWeight

1.50

et

1.49

noStroke

1.43

 those

1.42

 zaterdag

1.42

</strong>

1.41

 eorum

1.41

Activations Density 0.016%