INDEX

Explanations

Alain names

This neuron fires on occurrences of the given first name “Alan” (including the variant spelling “Alain”) in text.

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

 mirar

-0.83

 volatility

-0.77

 tumbling

-0.77

 shelling

-0.74

Есть

-0.70

gle

-0.70

tighet

-0.70

 wallpaper

-0.69

LoadScene

-0.69

Â

-0.68

POSITIVE LOGITS

 Verte

0.75

かも知

0.72

Vila

0.72

kati

0.71

haustible

0.71

Aar

0.70

رك

0.70

radan

0.69

 देते

0.69

'..

0.68

Activations Density 0.046%