INDEX

Explanations

work example expected issue

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

ην

-1.38

 السياس

-1.34

𓆏

-1.30

ığımız

-1.27

圌

-1.26

拌

-1.22

 asesino

-1.22

 vermel

-1.21

 flä

-1.20

atures

-1.19

POSITIVE LOGITS

1.53

1.15

1.13

Even

1.12

1.08

Nearly

1.06

就會

1.06

1.05

Once

1.04

Though

1.03

Activations Density 0.105%