INDEX

Explanations

imperative verbs and adverbs

The neuron activates on imperative or command phrases (e.g., “grow up,” “wake up,” “turn it off,” “stop it,” “go away”).

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

to

-1.70

 thanks

-1.13

 after

-1.06

ക്ഷ

-1.00

离去

-0.91

やま

-0.89

ines

-0.87

 perigo

-0.87

ană

-0.86

last

-0.86

POSITIVE LOGITS

now

1.48

 hoặc

1.41

 сейчас

1.31

 вже

1.30

 please

1.30

NOW

1.27

 already

1.27

或者

1.23

or

1.22

 или

1.21

Activations Density 0.023%