INDEX

Explanations

free details if email check for

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

 bilder

-1.35

 نیز

-1.34

 sinyal

-1.34

 rajut

-1.31

Läs

-1.30

 Nieuws

-1.27

 toit

-1.27

 Ekonomi

-1.27

 ekonomi

-1.26

 ings

-1.26

POSITIVE LOGITS

 only

1.61

to

1.48

see

1.38

 once

1.24

for

1.24

no

1.23

 from

1.20

 before

1.19

 barely

1.17

 without

1.16

Activations Density 0.056%