INDEX

Explanations

small

The neuron detects references to small‐sized items (e.g. the word “small” and other tokens indicating small objects or images).

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

-1.92

↵

-1.43

 Recher

-1.31

 about

-1.20

THE

-1.13

لول

-1.13

пать

-1.12

 different

-1.11

 primarily

-1.07

目は

-1.07

POSITIVE LOGITS

 kecil

2.13

small

1.88

一个小

1.75

Small

1.74

小的

1.70

 малень

1.69

kleine

1.63

 الصغيرة

1.59

小さな

1.48

เล็ก

1.48

Activations Density 0.243%