INDEX

Explanations

past actions or future plans

The neuron activates on words that name or describe communication formats or media channels (e.g. broadcast, radio, Twitter conversation, newsletter, technical report, website).

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

-2.31

 your

-2.27

are

-2.14

is

-1.84

 have

-1.63

has

-1.60

 today

-1.55

ığınız

-1.41

now

-1.39

Your

-1.39

POSITIVE LOGITS

was

2.13

 would

1.98

 وكان

1.73

 было

1.67

 وكانت

1.57

 ήταν

1.55

だったので

1.38

 skulle

1.38

дава

1.36

 damals

1.35

Activations Density 0.150%