INDEX

Explanations

run in a circle

The neuron fires strongly on colon punctuation (the “:” token).

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

ing

1.98

ния

1.59

ae

1.58

ة

1.58

[[

1.55

ியே

1.54

1.49

のが

1.45

ington

1.38

 வகையில்

1.38

POSITIVE LOGITS

ট

1.85

ਕ

1.55

dokkaHtml

1.45

")))

1.41

jenja

1.41

مر

1.38

א

1.38

""""

1.35

 PropTypes

1.30

س

1.29

Activations Density 0.307%