INDEX

Explanations

date contexts

The neuron detects mentions of dates (the token “date” or “dates”) in the text.

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

-1.91

atória

-1.84

]$

-1.84

 There

-1.79

 chimiques

-1.73

idoo

-1.73

}$

-1.72

）：

-1.71

ERICK

-1.71

ޏ

-1.70

POSITIVE LOGITS

of

2.13

 medarbe

2.02

 Giugno

1.95

 medlemmer

1.93

1.87

槼

1.78

ஂ

1.77

li

1.73

 samarbeid

1.69

 lakini

1.68

Activations Density 0.057%