INDEX

Explanations

boolean values

The neuron detects literal Boolean values (e.g. the tokens “true” and “false”).

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

 will

-1.41

of

-1.30

 ibang

-1.27

in

-1.22

carolina

-1.11

 just

-1.08

 usually

-1.07

 that

-1.04

 buhay

-1.03

 silang

-1.03

POSITIVE LOGITS

țial

1.23

ÉM

1.17

:'#

1.09

)!

1.06

 "");

1.05

!</

1.05

胳膊

1.04

 Rashford

1.03

 elke

1.02

”!

1.01

Activations Density 0.001%