INDEX

Explanations

that of phrase

The neuron is tuned to spot numeric or quantitative expressions (e.g. counts, measurements, statistics) 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

はこちらから

-1.54

 embalaje

-1.54

を読んで

-1.42

 pagado

-1.39

でしたね

-1.35

⏤

-1.34

 imprimible

-1.34

 ENGINEER

-1.33

んだよね

-1.32

 verschill

-1.30

POSITIVE LOGITS

1.48

–

1.36

*}$

1.33

</strong>

1.30

“

1.30

of

1.27

 sanoo

1.25

1.23

1.22

–

1.21

Activations Density 0.018%