INDEX

Explanations

does not exist

The neuron strongly responds to words and phrases that express non‐existence or negation—e.g. “doesn’t exist,” “did not exist,” “don’t … exist.”

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

of

-2.48

for

-1.84

-1.45

and

-1.34

-1.22

mLast

-1.21

 from

-1.20

 соответственно

-1.13

-1.12

POSITIVE LOGITS

it

1.69

 that

1.63

 aéreas

1.56

 acoged

1.48

 piscinas

1.37

the

1.34

 mochilas

1.34

 muualla

1.31

 productos

1.30

 they

1.30

Activations Density 0.186%