INDEX

Explanations

key players

The neuron selectively activates on occurrences of the noun “player” (especially its plural “players”).

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

’

-1.54

ků

-1.51

udnio

-1.50

AÇÃO

-1.49

hasilkan

-1.42

 antichi

-1.41

只有

-1.38

```

-1.35

-1.34

vají

-1.34

POSITIVE LOGITS

悪く

1.79

 игроков

1.73

くれて

1.72

少なく

1.66

 sauté

1.65

Ꮀ

1.65

齎

1.63

il

1.61

咥

1.59

1.58

Activations Density 0.015%