INDEX

Explanations

among others

The neuron flags instances of “among <n> others” count expressions.

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

 μὲν

-1.19

ございません

-1.09

した

-1.08

墳

-1.06

や

-1.05

 diseñar

-1.04

 تصریح

-1.04

PONE

-1.02

 aclarar

-1.02

 nhàng

-1.02

POSITIVE LOGITS

 other

2.27

 अन्य

1.85

 andere

1.67

 anderen

1.64

 diğer

1.62

 otras

1.61

 altre

1.58

 others

1.52

 다른

1.51

 دیگر

1.47

Activations Density 0.011%