INDEX

Explanations

getting or causing something

The neuron is detecting numeric tokens (numbers and numerical values) 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

-1.80

 such

-1.68

↵

-1.38

such

-1.34

目前的

-1.32

 būs

-1.25

儈

-1.24

 desastre

-1.23

 here

-1.21

ませんが

-1.20

POSITIVE LOGITS

you

3.19

</h1>

1.84

 people

1.57

 мужская

1.57

 deportivas

1.47

 цього

1.45

我們

1.44

we

1.41

him

1.41

 Министер

1.37

Activations Density 0.026%