INDEX

Explanations

rules, system, consistency

The neuron activates on numerical tokens and measurements (numbers, decimals, and other quantity 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

Usually

-1.31

 обычно

-1.26

Still

-1.22

Typically

-1.18

 usually

-1.16

 vesel

-1.15

Faça

-1.13

 suele

-1.10

いかがでしたか

-1.09

 деца

-1.04

POSITIVE LOGITS

 better

1.68

 proper

1.47

 improved

1.43

 properly

1.30

 uniform

1.24

 endlich

1.24

 наконец

1.16

 uniformity

1.15

better

1.13

 clearer

1.13

Activations Density 0.029%