INDEX

Explanations

followed by punctuation or separators

The neuron fires on mentions of specific places or venue names (e.g. guesthouse names, map spots, geographic locations).

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

<eos>

1.29

/'

0.69

টেও

0.67

:'

0.66

;'

0.64

:'.

0.64

''.

0.64

\/

0.63

៕

0.61

=.

0.61

POSITIVE LOGITS

 দার্শন

0.84

 多く

0.80

 這個

0.76

 നിരവധി

0.75

 我們

0.73

 それぞれ

0.72

 Unlike

0.72

 Mỗi

0.72

 YouTuber

0.71

 Это

0.71

Activations Density 0.000%