INDEX

Explanations

if clause examples

The neuron flags numeric tokens or explicit number mentions in text.

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

↵↵

-1.77

rdag

-1.48

mayın

-1.42

他

-1.33

相关

-1.32

unteers

-1.28

或

-1.27

 cuchara

-1.25

madı

-1.24

↵

-1.23

POSITIVE LOGITS

 your

1.73

–)

1.43

wwww

1.39

1.38

)]:

1.37

Референце

1.31

 '/':

1.30

 ($('#

1.30

当时的

1.29

'~

1.28

Activations Density 0.205%