INDEX

Explanations

named entity or description

The neuron fires on occurrences of “named” (especially capitalized “Named”) in code identifiers or imports.

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

Deals

-0.90

UNG

-0.90

Frédéric

-0.84

Trails

-0.82

deals

-0.81

jerne

-0.81

Streamer

-0.81

dragons

-0.79

Rhin

-0.79

 prefeitura

-0.78

POSITIVE LOGITS

named

1.07

tuple

1.02

 Named

0.94

arg

0.91

Named

0.90

Пі

0.87

uses

0.84

Uses

0.83

 named

0.83

IsTrue

0.81

Activations Density 0.020%