INDEX

Explanations

stating findings and conclusions

This neuron activates on numeric tokens, i.e. 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

in

-1.63

 this

-1.45

or

-1.45

on

-1.43

 after

-1.31

 when

-1.29

at

-1.23

 during

-1.23

 kaynağından

-1.21

 would

-1.17

POSITIVE LOGITS

 there

1.40

 largely

1.37

 certain

1.30

どうやら

1.29

 parece

1.27

やっぱ

1.23

1.22

Seems

1.21

 diverses

1.19

generally

1.18

Activations Density 0.103%