INDEX

Explanations

time measured in years

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

',

-1.44

谡

-1.42



-1.39

,\\

-1.38

'./

-1.37

ͱ

-1.29

ūras

-1.27

晳

-1.26

촨

-1.26

ruguay

-1.26

POSITIVE LOGITS

in

1.61

 détaillée

1.34

лі

1.29

1.25

得

1.23

 actuelle

1.23

</b>

1.22

 years

1.16

 серия

1.16

why

1.16

Activations Density 0.064%