INDEX

Explanations

technical identifiers and keywords

The neuron specifically lights up on programming identifier tokens—names of types, functions, methods, or variables (e.g. CamelCase or snake_case code symbols).

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

of

-1.62

 which

-1.49

 their

-1.28

as

-1.20

 with

-1.17

 antichi

-1.16

but

-1.12

all

-1.09

 them

-1.09

後は

-1.09

POSITIVE LOGITS

鸲

1.25

FONTE

1.22

 таких

1.22

asthan

1.17

 portatil

1.17

另一

1.16

乄

1.16

 améli

1.16

Etiquetas

1.15

 something

1.14

Activations Density 0.039%