INDEX

Explanations

lists of topics

The neuron detects section headings or titles (e.g. capitalized phrases introducing a new section, often ending with a colon or question mark).

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

-2.05

was

-1.85

of

-1.70

-1.62

-1.61

-1.59

an

-1.58

--

-1.57

-1.56

POSITIVE LOGITS

you

1.87

 tega

1.85

 stolet

1.78

 šte

1.75

↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵

1.74

 ujedno

1.69

 acompañado

1.66

↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵

1.66

 drugim

1.63

↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵

1.63

Activations Density 0.015%