INDEX

Explanations

determiners followed by nouns

The neuron strongly responds to occurrences of the word “other.”

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

 Não

-1.63

–¿

-1.62

鈊

-1.55

 Información

-1.45

那里

-1.41

 Tienen

-1.41

 Tenemos

-1.40

 Otras

-1.38

 pulseira

-1.33

玊

-1.33

POSITIVE LOGITS

or

1.89

又は

1.45

 veya

1.44

หรือ

1.34

 then

1.34

 یا

1.33

 podían

1.32

元々

1.32

ınız

1.29

 čia

1.27

Activations Density 0.323%