INDEX

Explanations

invention or subject and what relates to it

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

 великолеп

-1.62

냑

-1.41

 восхи

-1.40

 высокая

-1.39



-1.37

Mejores

-1.34

漂亮的

-1.33

 больших

-1.32

‫‪

-1.32

 тща

-1.31

POSITIVE LOGITS

of

3.36

 will

2.05

in

1.91

1.87

on

1.77

for

1.73

you

1.70

was

1.70

 should

1.66

or

1.59

Activations Density 0.255%