INDEX

Explanations

references to advanced mathematical concepts and notation

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.51

-0.50

Ngh

-0.49

 IOError

-0.49

 jednou

-0.49

}{{\

-0.48

}}\

-0.48

 Kien

-0.48

trá

-0.47

))\

-0.47

POSITIVE LOGITS

_{

1.90

_{\

1.55

}_{

1.53

_{

1.44

}_{

1.30

$_{

1.28

<sub>

1.27

}_{\

1.23

]_{

1.20

$_{

1.19

Activations Density 6.326%