INDEX

Explanations

these / this (languages)

The neuron fires on words that occur at the start of a sentence (i.e. capitalized sentence-initial function words and pronouns).

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

 from

-1.40

 just

-1.39

it

-1.38

 because

-1.38

by

-1.31

 considerable

-1.20

 only

-1.19

on

-1.18

 first

-1.16

 three

-1.16

POSITIVE LOGITS

 these

2.22

这些

2.16

這些

1.87

これらの

1.86

 этих

1.81

these

1.77

 इन

1.71

 essas

1.68

 همچنین

1.67

 acestea

1.60

Activations Density 0.097%