INDEX

Explanations

fullness and satisfaction

The neuron activates on words and word fragments that describe hunger, fullness, or satiety levels.

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

to

-1.46

梟

-1.34

 lemah

-1.30

 detrás

-1.29

、“

-1.28

 allá

-1.28

狛

-1.27

 خریدار

-1.26

béco

-1.24

rinol

-1.24

POSITIVE LOGITS

 Съ

1.38

来找

1.37

翻译

1.34

sâ

1.27

مان

1.27

 städ

1.25

 mân

1.24

wendige

1.23

 větší

1.23

 satisfied

1.23

Activations Density 0.012%