INDEX

Explanations

probability and likelihood

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

but

-2.05

ܜ

-1.96

輊

-1.86

 seront

-1.84

喾

-1.81

 visualización

-1.78

௅

-1.77

⦊

-1.77

现在

-1.76

忽然

-1.68

POSITIVE LOGITS

もある

2.14

なお

1.75

ｹ

1.69

余談

1.69

い

1.64

ｶ

1.64

人を

1.63

olverine

1.60

bestos

1.57

という感じ

1.57

Activations Density 0.015%