INDEX

Explanations

congressional committees

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

“

-1.55

-1.48

 herbe

-1.38

-1.32

 Eigentü

-1.29

 يس

-1.26

was

-1.25

-1.24

 даже

-1.23

าก็

-1.20

POSITIVE LOGITS

mathrm

1.66

？』

1.35

érieures

1.34

 komplette

1.33

⩤

1.31

 onderdelen

1.29

 которого

1.28

manız

1.26

 gerçekten

1.26

')

1.25

Activations Density 0.025%