INDEX

Explanations

thing about / thing to

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

 esencial

-1.81

蛲

-1.73

zwi

-1.73

#%%

-1.73

 motocicletas

-1.72

 cajas

-1.66

莛

-1.64

 caminando

-1.63

 sillas

-1.62

 baterías

-1.61

POSITIVE LOGITS

of

2.30

to

2.25

 this

1.55

ными

1.52

end

1.48

 должен

1.38

 ваше

1.36

いかがでしたか

1.34

 они

1.33

 ところ

1.30

Activations Density 0.016%