INDEX

Explanations

banking and political entities

The neuron fires on tokens that contain or begin with uppercase letters—e.g. proper nouns, section headings, acronyms, and other capitalized 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

ul

1.15

1.10

re

1.09

sh

0.95

0.91

lös

0.90

lad

0.88

ör

0.85

sas

0.84

POSITIVE LOGITS

 livré

0.91

যুদ্ধ

0.89

щении

0.88

 heyday

0.83

 verpflichtet

0.83

᱗

0.83

 anmelden

0.82

 kısmı

0.81

 Combien

0.81

 cometido

0.80

Activations Density 0.001%