INDEX

Explanations

checks variable type

The neuron is primarily detecting numeric tokens (i.e. tokens made up of digits).

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

 departamento

0.90

芏

0.89

鄧

0.84

tevõ

0.82

 departamentos

0.80

 beschäft

0.80

ikova

0.80

 Dahmer

0.79

<unused53>

0.79

 Higgins

0.79

POSITIVE LOGITS

}\

0.72

Page

0.71

 corrobor

0.68

 enclosing

0.65

 coincides

0.64

 else

0.64

सोई

0.63

PY

0.62

iles

0.62

 induces

0.61

Activations Density 0.002%