INDEX

Explanations

words followed by than

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

oterapia

1.07

 assolutamente

1.06

 suficiente

1.05

 amplo

1.04

とても

1.00

非常に

1.00

での

0.98

すごく

0.97

 sangat

0.95

 máximo

0.95

POSITIVE LOGITS

 than

3.69

 Than

3.15

than

3.14

Than

2.93

 niż

2.81

än

2.45

 THAN

2.28

 kuin

2.16

 dibanding

2.05

 než

1.91

Activations Density 0.596%