INDEX

Explanations

This is a description

The neuron strongly activates on the demonstrative phrase “This is” (i.e. sentences beginning with “This is …”).

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

 reager

-1.38

एक

-1.38

 pastillas

-1.33

*///

-1.31

Или

-1.27

 parlement

-1.25

ingan

-1.23

 এবং

-1.20

Erreur

-1.20

 annet

-1.19

POSITIVE LOGITS

 Still

1.42

but

1.41

to

1.37

 still

1.30

]<<"

1.28

↵↵

1.27

if

1.23

 depuis

1.23

 less

1.22

ofür

1.22

Activations Density 0.083%