INDEX

Explanations

connecting clauses or items

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

antaine

-1.16

以免

-1.15

to

-1.10

 myös

-1.08

眈

-1.05

<<<<<<<

-1.02

umers

-1.02

茳

-1.01

ienne

-1.01

 también

-1.01

POSITIVE LOGITS

 then

3.95

it

2.72

not

2.33

 still

2.22

 THEN

2.13

 have

1.98

 nobody

1.85

 тогда

1.85

 there

1.76

 потом

1.72

Activations Density 0.086%