INDEX

Explanations

deal, agreement, treaty

The neuron activates on mentions of formal agreements or deals (e.g. “deal,” “agreement,” “treaty”).

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

 její

-1.52

и

-1.45

 například

-1.44

 και

-1.43

ными

-1.37

-1.34

gemar

-1.34

เรา

-1.32

 więc

-1.32

岀

-1.30

POSITIVE LOGITS

 harán

1.47

 Schluß

1.38

Exelente

1.37

コスパ

1.37

もう一度

1.35

不會

1.35

ಞ

1.31

Mejor

1.30

鐒

1.28

何より

1.27

Activations Density 0.026%