INDEX

Explanations

questions in multiple languages

The neuron responds to unusually long runs of whitespace (indentation or large blank gaps).

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



-1.30

ᵉ

-1.28

testCase

-1.27

︓

-1.26

⃢

-1.22

ʰ

-1.18

 Baños

-1.17

avond

-1.16

 sammen

-1.14

 conséquent

-1.14

POSITIVE LOGITS

 folgt

1.40

 الحكومة

1.40

 fünf

1.34

都想

1.30

 jednej

1.30

才可以

1.25

 procedimento

1.24

 solchen

1.24

nové

1.23

 wonderful

1.22

Activations Density 0.010%