INDEX

Explanations

place names and surnames

The neuron selectively activates on capitalized proper nouns—names of characters, places, organizations, and other named entities.

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

-1.63

 laikā

-1.55

 with

-1.49

 what

-1.42

 sometimes

-1.41

 which

-1.32

 when

-1.28

</u>

-1.27

 udało

-1.23

 that

-1.23

POSITIVE LOGITS

WriteLiteral

1.41

ßten

1.40

 nerv

1.38

竟然是

1.26

 surpris

1.26

НОГО

1.26

vada

1.25

对你

1.24

 provid

1.23

もしれない

1.22

Activations Density 0.048%