INDEX

Explanations

board games and associated terms

The main thing this neuron does is spot mentions of “board games” (or the words “board” and “game(s)” in that context).

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

尨

-2.53

 raiſ

-2.14

垸

-2.09

 bordados

-1.98

卧槽

-1.95

୬

-1.94

圌

-1.94

 italianos

-1.93

很赞

-1.91

螣

-1.91

POSITIVE LOGITS

2.30

</em>

2.22

2.03

 Although

1.91

Not

1.88

 Despite

1.85

但在

1.82

 Though

1.77

 автомо

1.77

Activations Density 0.040%