INDEX

Explanations

presence in or on

This neuron activates on occurrences of the word “presence.”

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

</i>

-1.69

 mußte

-1.63

The

-1.62

ጪ

-1.43

梿

-1.41

 acrescent

-1.41

 abbin

-1.41

 cammino

-1.41

</td>

-1.38

astră

-1.37

POSITIVE LOGITS

in

1.78

on

1.48

1.37

他想

1.34

<bos>

1.25

割合

1.24

1.23

ent

1.22

 decisões

1.20

of

1.19

Activations Density 0.031%