INDEX

Explanations

print and output

The main thing this neuron does is find mentions of printing (e.g., “print,” “printed,” “print out,” “printout”).

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

you

-2.02

↵↵↵

-1.77

-1.43

把自己

-1.36

 each

-1.33

羚

-1.33

来る

-1.32

 elige

-1.29

 elevate

-1.28

OOOOOO

-1.27

POSITIVE LOGITS

婓

1.86

INTAIN

1.64

 männer

1.62

 cejas

1.59

 kılıf

1.55

 erhi

1.46

 giud

1.45

⼥

1.44

緜

1.44

vedades

1.43

Activations Density 0.020%