INDEX

Explanations

pronoun followed by verb

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

of

-2.00

and

-1.87

on

-1.63

 every

-1.41

at

-1.39

in

-1.35

på

-1.33

 during

-1.24

 from

-1.23

no

-1.20

POSITIVE LOGITS

iações

1.34

 sels

1.34

 プル

1.30

 chariots

1.30

 pensare

1.30

 impieg

1.29

 utilizz

1.27

 pite

1.27

 spiega

1.27

 parlare

1.27

Activations Density 0.110%