INDEX

Explanations

HBO and TV shows

The neuron activates on mentions of television network or channel names (e.g., HBO, FX, FXX, TNT, TBS).

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

たまた

-1.77

 possiamo

-1.68

靣

-1.52

 fornire

-1.48

 portatil

-1.47

ならでは

-1.44

その後

-1.42

ÁCT

-1.39

 perfeitamente

-1.39

媜

-1.38

POSITIVE LOGITS

):

1.72

↵↵

1.46

</h5>

1.23

zboi

1.21

1.20

щика

1.20

ilización

1.19

」、

1.17

1.16

 viernes

1.16

Activations Density 0.012%