INDEX

Explanations

hair ties

The neuron is strongly activated by relatively rare, content‐bearing tokens (e.g. uncommon nouns, verbs in –ing, numbers, adverbs) rather than by high‐frequency function 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

Ess

0.77

叶

0.75

SC

0.74

гі

0.74

레

0.74

Border

0.73

Ві

0.73

ش

0.73

Education

0.73

на

0.72

POSITIVE LOGITS

 Golpe

0.88

 synced

0.86

 sostuvo

0.84

 dejo

0.84

 referencias

0.82

zyg

0.82

 Robo

0.80

 fundamento

0.80

 legible

0.79

 cambiar

0.78

Activations Density 0.000%