INDEX

Explanations

code, commands, or data parsing

The neuron fires on integer literal tokens (numeric constants) in code.

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

recent

-1.00

ǟ

-1.00

owing

-0.90

ICIAS

-0.90

wns

-0.89

recently

-0.89

पि

-0.89

 récemment

-0.87

 recente

-0.85

Año

-0.85

POSITIVE LOGITS

 from

1.20

 their

1.16

 more

0.89

 during

0.88

by

0.87

 said

0.87

 still

0.82

 between

0.77

бота

0.77

hawat

0.77

Activations Density 0.003%