INDEX

Explanations

toilet or terminals

The neuron fires on mentions of toilets and their components or flushing mechanisms.

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

-1.41

笮

-1.40

 pflegen

-1.39

已然

-1.36

嫱

-1.34

étape

-1.34

进入了

-1.30

 pretože

-1.30

utilité

-1.30

 NEED

-1.30

POSITIVE LOGITS

MATIC

1.36

☑️

1.28

));

1.20

💩

1.20

amplitude

1.16

ゃ

1.14

byes

1.13

８

1.10

結合

1.10

hoku

1.10

Activations Density 0.021%