INDEX

Explanations

funding sources and entities

The neuron activates on monetary and numeric funding figures (e.g. grant amounts and dollar values).

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

Leírás

-1.51

Sådan

-1.37

 好看

-1.37

 aproximativ

-1.35

possibly

-1.34

usions

-1.32

THEY

-1.30

hommes

-1.28

atized

-1.27

Evet

-1.25

POSITIVE LOGITS

 from

2.05

 then

1.75

 through

1.74

 after

1.55

 what

1.38

1.33

 their

1.32

 would

1.32

 want

1.29

so

1.28

Activations Density 0.060%