INDEX

Explanations

Peter Rost name

The neuron fires on the “setting” of a value in code—i.e. on assignment targets or setter declarations.

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

 from

-1.25

his

-1.16

 like

-1.15

postolic

-1.12

Dě

-1.11

of

-1.11

 which

-1.10

 Popis

-1.09

 també

-1.09

the

-1.09

POSITIVE LOGITS

事实上

1.23

もありました

1.20

我們

1.18

1.12

($__

1.09

 exhib

1.08

─

1.05

 hauptsächlich

1.05

トゥ

1.05

ー

1.04

Activations Density 0.000%