INDEX

Explanations

"one" or "at" sequences

This neuron is sensitive to content-bearing nouns and verbs that introduce key entities or events in the text.

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

 kaikki

0.93

 semua

0.89

すべての

0.87

सभी

0.86

 both

0.86

 tutte

0.85

各个

0.84

 любых

0.83

 любые

0.83

 सभी

0.82

POSITIVE LOGITS

 unui

1.59

 unei

1.43

 isang

1.40

 seorang

1.38

 einer

1.35

 sebuah

1.35

 ενός

1.34

某

1.34

 Sebuah

1.33

eseorang

1.31

Activations Density 1.065%