INDEX

Explanations

demonstrative or possessive follows "of"

The neuron fires on numeric values and isolated numbers (e.g. percentages, measurements, citation numbers) 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

 what

-1.16

dropIfExists

-1.12

 things

-1.12

all

-1.11

 تھے

-1.09

 além

-1.04

millan

-1.04

つまり

-1.04

 change

-1.03

:+:

-1.02

POSITIVE LOGITS

 this

2.70

 these

2.13

 этого

1.95

この

1.89

はこの

1.82

 این

1.80

 هذه

1.76

 dieser

1.68

its

1.62

 этой

1.59

Activations Density 0.288%