INDEX

Explanations

regression coefficients and variables

The neuron activates on mentions of regression operations—words like “regress,” “regression,” or “regressing.”

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

who

-1.50

 first

-1.39

 votre

-1.31

},

-1.26

 about

-1.25

 with

-1.20

 también

-1.20

 også

-1.18

 otros

-1.17

 musst

-1.16

POSITIVE LOGITS

the

1.41

 evin

1.23



1.22

ции

1.19

...

1.17

HOLD

1.16

的脸

1.13

 masina

1.13

еве

1.12

 exorbit

1.11

Activations Density 0.031%