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

нём

1.88

чё

1.87

чён

1.83

ёв

1.81

вёр

1.76

жён

1.76

 её

1.76

ё

1.74

ётся

1.71

ড়িয়ে

1.67

POSITIVE LOGITS

 accorded

2.65

 hitherto

2.56

 envisaged

2.55

 envis

2.42

ਸ਼

2.37

 duly

2.29

itherto

2.24

 tranche

2.23

 invariably

2.23

 meagre

2.22

Activations Density 0.174%

No Known Activations