INDEX

Explanations

units of measurement

The neuron activates on numeric tokens, especially decimal or measurement values.

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

 with

-1.63

-1.48

any

-1.45

-1.42

[];

-1.41

 אבל

-1.33

 tikra

-1.31

to

-1.28

りますが

-1.27

POSITIVE LOGITS

érieur

1.55

şem

1.55

婁

1.52

you

1.51

ご了承ください

1.50

相比

1.49

INTAIN

1.47

性的

1.46

 obiek

1.46

erializer

1.45

Activations Density 0.101%