INDEX

Explanations

comedy series and films

The neuron detects occurrences of the word “comedy” (or closely related mentions of the comedy genre).

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

-3.13

?"

-2.78

会

-2.72

 cual

-2.52

 включая

-2.47

扨

-2.41

unicaciones

-2.39

注意事

-2.39

os

-2.38

再加上

-2.36

POSITIVE LOGITS

3.36

龊

2.75

 haberse

2.34

the

2.31

zelfde

2.30

 verschil

2.28

 nehé

2.28

2.23

蘼

2.22

 bicicletas

2.16

Activations Density 0.002%