INDEX

Explanations

biblical names and places

This neuron detects numeric tokens (e.g. verse numbers, float or integer values, and other numeric references) in the text.

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

廡

-1.62

 TWENTY

-1.47

laje

-1.47

-1.46

 bedien

-1.45

 Modules

-1.42

and

-1.41

 basado

-1.40

摟

-1.38

 хуже

-1.37

POSITIVE LOGITS

しました

1.55

at

1.41

 markedly

1.39

 druge

1.36

</h5>

1.36

منون

1.34

 some

1.34

 mighty

1.33

 zelo

1.33

</b>

1.32

Activations Density 0.002%