INDEX

Explanations

it like, it when

The neuron is primarily triggered by the pronoun “it” (and closely associated simple auxiliaries like “did,” “get,” “know,” etc.).

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

ться

1.27

 وعلى

1.16

ের

1.10

ులు

1.09

及び

1.05

↵

1.05

ствен

1.04

ции

1.03

мни

1.03

 receptacles

1.00

POSITIVE LOGITS

ty

1.09

lių

1.07

เตอร์

1.05

 pamoja

1.02

<bos>

1.00

 Tecnología

0.99

lan

0.98

ました

0.98

spanish

0.98

ong

0.97

Activations Density 0.123%