INDEX

Explanations

#include and #load directives

The neuron activates on hash (“#”) characters used as line prefixes (e.g. preprocessor directives or Markdown headings).

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

and

-2.02

 even

-1.69

where

-1.50

st

-1.48

他没有

-1.43

 with

-1.38

と話

-1.37

-1.33

Тогда

-1.33

他已经

-1.33

POSITIVE LOGITS

 veröffentlich

1.66

ፁ

1.66

哙

1.61

了

1.57

 präsenti

1.57

eluarkan

1.55

睃

1.55

 ส์

1.54

 frattempo

1.54

 VERY

1.53

Activations Density 0.014%