INDEX

Explanations

end of quote followed by speech verbs

This neuron detects dialogue attribution—instances of quoted speech together with the accompanying tag (e.g. “,” said, “?” asked, “,” he hissed, “,” growled, etc.).

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

问道

-1.18

 OGSÅ

-1.05

 Fragen

-1.00

に行く

-1.00

 هذه

-0.98

 Así

-0.96

 này

-0.94

 هذا

-0.94

\[

-0.93

 primeiro

-0.91

POSITIVE LOGITS

 came

1.25

 comes

1.09

Fá

1.08

issements

1.07

 prêtre

1.06

 said

1.05

 they

1.04

Raúl

1.03

Frédéric

0.98

Samedi

0.93

Activations Density 0.003%