INDEX

Explanations

movement

The neuron activates on words that denote movement—especially various forms of the verb “move” (move, moved, moving, moves, etc.).

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

ulihan

-1.52

奚

-1.34

 success

-1.31

стом

-1.30

々な

-1.29

має

-1.28

 Evangelical

-1.26

沨

-1.25

 portrayal

-1.25

 הם

-1.22

POSITIVE LOGITS

ay

1.46

 ближе

1.34

还可以

1.32

ﬃ

1.28

 menyebut

1.28

 olika

1.26

。『

1.24

ag

1.21

 tillbaka

1.21

Activations Density 0.049%