INDEX

Explanations

suggest alternative activity

This neuron flags contentful nouns and verbs typical of formal, legal-oriented or business-style prose.

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

För

0.75

Tenemos

0.71

Balls

0.71

 নিয়েছে

0.70

િલ્

0.68

ডেল

0.68

เ

0.68

๙

0.66

Dent

0.65

Это

0.65

POSITIVE LOGITS

 desi

0.95

irat

0.94

lardan

0.87

 strategi

0.85

leni

0.82

sq

0.77

টিআই

0.77

 sanctity

0.77

si

0.75

lé

0.75

Activations Density 0.000%