INDEX

Explanations

asking for context or specifics

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

 Име

2.70

emu

2.28

şey

2.24

emuan

2.21

 Einige

2.19

ونکو

2.14

emiz

2.13

обходимо

2.13

rino

2.11

ап

2.09

POSITIVE LOGITS

 forKey

2.29

ுள்ளார்

1.97

 partial

1.94

ढ़े

1.91

ுள்ளனர்

1.88

wedge

1.88

벳

1.87

タニ

1.85

definite

1.81

恿

1.81

Activations Density 0.407%