INDEX

Explanations

class and interface definitions

This neuron detects occurrences of the colon character “:” used in code (e.g. for class inheritance or type annotations).

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

見えます

-1.48

thodoxy

-1.18

utenants

-1.15

搅拌

-1.13

碓

-1.12

そして

-1.11

サイズの

-1.10

臵

-1.09

 العديد

-1.09

Boxscore

-1.07

POSITIVE LOGITS

 manquante

1.42

 people

1.23

 appelez

1.17

 things

1.16

 pensez

1.11

に似

1.11

 very

1.10

 voyez

1.09

 greatly

1.09

 obiet

1.07

Activations Density 0.012%