INDEX

Explanations

outcomes and results

The neuron fires on numeric score and statistic tokens—i.e. it’s looking for numbers (often sports‐related scores or stats) 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

蕺

-1.66

 abbildung

-1.53

橚

-1.52

 développer

-1.51

౭

-1.51

湏

-1.49

 marquer

-1.47

 décider

-1.47

 pourront

-1.45

敺

-1.44

POSITIVE LOGITS

by

2.00

 from

1.59

in

1.47

on

1.43

not

1.38

 said

1.31

 themselves

1.27

ฯ

1.27

via

1.25

.(

1.22

Activations Density 0.022%