INDEX

Explanations

place names

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

 addressing

-1.11

 believes

-1.03

 started

-1.03

 first

-1.00

 probably

-0.99

 what

-0.98

 only

-0.97

at

-0.97

 begin

-0.94

 highlighting

-0.94

POSITIVE LOGITS

 village

1.27

really

1.06

 mesmas

1.06

 autorisés

1.06

stown

1.02

Village

0.99

 Village

0.99

nymi

0.97

ことができ

0.97

remark

0.96

Activations Density 0.106%