INDEX

Explanations

every other number

The neuron activates on semantically rich “content” words (nouns, verbs, adjectives, adverbs) rather than on common 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

тэй

0.90

sinh

0.90

 использования

0.85

din

0.83

sin

0.81

sing

0.80

 Ansatz

0.80

gene

0.80

UserProfile

0.80

 sensitization

0.79

POSITIVE LOGITS

ो

0.75

और

0.73

 شرا

0.73

 suffice

0.69

 등이

0.66

들을

0.66

]-->

0.66

들의

0.66

 тощо

0.65

Activations Density 0.000%