INDEX

Explanations

credit card

The neuron fires on isolated non-letter symbols (such as standalone digits in version numbers or punctuation like a closing curly brace).

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

 évé

-1.38

 seizoen

-1.30

 conseille

-1.27

 bré

-1.27

 Automó

-1.24

 Polskiej

-1.22

 cerro

-1.20

laatst

-1.20

 norvég

-1.20

 réus

-1.20

POSITIVE LOGITS

 figliu

1.12

 culturale

1.09

 gegenwär

1.09

 Coroner

1.08

這些

1.05

 erwähnten

1.05

SOME

1.02

fl

1.02

küche

1.02

 大きい

1.02

Activations Density 0.000%