INDEX

Explanations

specific data concepts

This neuron detects words that occur at the ends of sentences or clauses (i.e., sentence-final tokens).

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

0.85

 gemäß

0.82

0.80

،

0.80

 بقول

0.77

 такой

0.77

зыва

0.73

 foolproof

0.73

 tough

0.73

sekten

0.73

POSITIVE LOGITS

ті

0.95

 résident

0.90

enregistrement

0.83

 Règ

0.81

 travailler

0.79

સ

0.78

ኛ

0.78

 tirer

0.77

裵

0.77

minecraft

0.76

Activations Density 0.000%