INDEX

Explanations

Vorskla or similar endings

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 rangka

1.40

 brutal

1.36

মাদের

1.36

 kurang

1.33

 이런

1.28

elegant

1.27

},}

1.27

 그렇게

1.25

𝑢

1.25

 열심히

1.25

POSITIVE LOGITS

1.43

ires

1.39

hetics

1.37

presso

1.21

mor

1.20

altro

1.20

લ્પ

1.16

ges

1.16

oncesto

1.16

мир

1.16

Activations Density 0.018%