INDEX

Explanations

sale or sales followed by data

This neuron activates on occurrences of the word “sale” or “sales” (in any context or compound) within 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

felpa

-2.44

瑨

-2.02

 kullanıcı

-2.00

</h4>

-1.95

 şirket

-1.94



-1.93

ATION

-1.91

 gerekli

-1.88

嬲

-1.86

 transmiti

-1.85

POSITIVE LOGITS

 '*':

2.02

</i>

2.02

is

1.94

 armé

1.83

who

1.83

1.80

ar

1.78

 '-':

1.77

Name

1.77

and

1.77

Activations Density 0.006%