INDEX

Explanations

No Explanations Found

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

จ

1.77

(!)

1.59

(!)

1.55

1.54

(!

1.43

 כא

1.41

รร

1.36

(!

1.34

fra

1.27

 própria

1.27

POSITIVE LOGITS

 heterogeneous

2.12

 interrelated

1.92

 identifies

1.79

 predetermined

1.79

 위하여

1.78

 dominions

1.77

 interdependent

1.75

 행동

1.72

<unused2206>

1.68

সহিত

1.68

Activations Density 0.235%

No Known Activations