INDEX

Explanations

summer and winter

The neuron activates on words referring to seasons or climate conditions (e.g., “winter,” “summer,” “seasons,” “climates”).

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

écart

-1.44

 their

-1.40

satin

-1.34

􀂃

-1.32

 comercial

-1.30

ждению

-1.28

旗下

-1.26

盉

-1.24

pullover

-1.24

 kiedyś

-1.23

POSITIVE LOGITS

time

1.27

 тех

1.24

object

1.21

he

1.19

};

1.16

 celles

1.14

His

1.10

kes

1.07

iendo

1.07

My

1.06

Activations Density 0.054%