INDEX

Explanations

greetings and names

The neuron fires on valedictions—i.e. the sign-off phrases (like “Regards,” “Love …,” “Thanks,” “XO,” etc.) marking the end of a message.

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

now

-1.08

ついで

-1.05

satunya

-1.02

외부

-0.93

入り口

-0.92

経緯

-0.92

巿

-0.91

 stanga

-0.89

 misericordia

-0.88

 größer

-0.86

POSITIVE LOGITS

"./

1.07

season

1.05

recogn

1.03

 luzes

1.02

lepší

1.02

 reconhe

1.02

Thank

1.02

Thanks

1.02

 ajustable

1.01

strictEqual

1.01

Activations Density 0.015%