INDEX

Explanations

AI assistant refusals

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

 trow

2.04

 emerges

1.94

inderung

1.94

<0x0C>

1.93

 unveil

1.90

 emerge

1.86

 processions

1.84

 comedic

1.83

 operands

1.80

 surpass

1.79

POSITIVE LOGITS

 takže

1.47

 então

1.29

しているので

1.25

っているので

1.19

 그러니까

1.12

我很

1.12

 nên

1.07

不久

1.05

 있는데

1.05

なので

1.05

Activations Density 0.446%