INDEX

Explanations

comparing differences and similarities

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

 also

-1.20

他是

-1.15

<h2>

-1.14

%">

-1.13

it

-1.11

 कौन

-1.11

ньому

-1.10

))));

-1.10

);

-1.10

POSITIVE LOGITS

 what

3.19

 that

2.88

 those

2.41

how

2.34

 other

2.16

the

2.16

 آنچه

1.93

 others

1.90

 previous

1.68

 earlier

1.55

Activations Density 0.075%