INDEX

Explanations

want company or ancestry

The neuron fires most strongly on relatively rare or specialized tokens—that is, uncommon vocabulary words.

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

 three

0.68

 predicted

0.68

 four

0.68

 projected

0.63

 thirty

0.61

 test

0.61

βα

0.61

0.60

rm

0.60

 toss

0.60

POSITIVE LOGITS

 alku

0.93

هایی

0.90

evším

0.88

های

0.87

 ampio

0.86

不说

0.86



0.85

 terapi

0.84

呯

0.83

 deiner

0.81

Activations Density 0.001%