INDEX

Explanations

enum, classification, or type

This neuron fires on the names of configuration parameters or option fields (typically uppercase or code-style identifiers like TYPE, PARAM_TYPE, DISPLAY_TYPE, LTY, etc.) in technical or API documentation.

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

ണ്ടു

0.59

ouz

0.56

 комплек

0.55

 فلسط

0.54

 vineyards

0.54

ണ്ട

0.53

ৌজ

0.52

🦇

0.52

 fluorescence

0.51

 বহু

0.51

POSITIVE LOGITS

Enum

1.83

 enum

1.80

 Enum

1.66

enum

1.52

ENUM

1.27

EnumValue

1.16

switch

1.13

 switch

1.12

enums

1.10

 type

1.09

Activations Density 0.104%