INDEX

Explanations

numerical ranges, prices, or durations

The neuron is tuned to pick up numeric information—tokens representing numbers, quantities, prices, or other numeric data.

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

を

-1.74

は

-1.51

<bos>

-1.45

 several

-1.43

in

-1.39

と

-1.37

 both

-1.33

が

-1.26

 και

-1.20

や

-1.16

POSITIVE LOGITS

場所で

1.34

ところに

1.33

ことも

1.30

님

1.30

 semblables

1.30

 ngào

1.26

様な

1.23

ようで

1.21

 podendo

1.21

 cubiertos

1.20

Activations Density 0.003%