INDEX

Explanations

why is it that

The neuron fires on occurrences of personal pronouns (especially “you,” “it,” and “they”) and forms of the verb “to be” (is/are/re) in the text.

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

If

-1.48

Tempat

-1.40

Catatan

-1.38

彿

-1.37

 yayın

-1.37

camisas

-1.35

Tahun

-1.34

如果不是

-1.34

汕

-1.31

ématiques

-1.30

POSITIVE LOGITS

you

1.70

</i>

1.61

why

1.57

</h1>

1.57

 they

1.51

da

1.49

),

1.48

ية

1.48

YECTO

1.48

></

1.42

Activations Density 0.010%