INDEX

Explanations

first in other languages

This neuron detects idiomatic discourse markers introducing personal advice or opinion (e.g. “when it comes to…” and “in my experience…”).

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

 also

-2.44

 также

-1.81

 також

-1.73

 também

-1.71

 myös

-1.66

 również

-1.61

 επίσης

-1.60

 également

-1.54

อีก

-1.54

Also

-1.49

POSITIVE LOGITS

 first

2.17

 første

1.97

 eerste

1.88

的第一

1.84

 ersten

1.80

 první

1.72

 första

1.70

 primeira

1.69

第一

1.63

 πρώ

1.63

Activations Density 0.068%