INDEX

Explanations

i followed by specific word endings

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

-3.13

is

-2.48

-2.17

 However

-1.98

 либо

-1.95

</h2>

-1.92

”;

-1.87

end

-1.83

系の

-1.77

 otra

-1.69

POSITIVE LOGITS

鲞

2.09

 markiert

2.08

養

2.05

 način

1.99

ꦠ

1.98

鐿

1.97



1.97

 schli

1.94

?"

1.93

 seleccionadas

1.92

Activations Density 0.001%