INDEX

Explanations

demonstrative 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

No Comments

Negative Logits

 они

-1.14

his

-1.13

 оно

-1.01

arture

-0.97

 его

-0.95

 она

-0.94

它的

-0.93

 those

-0.91

its

-0.90

inawa

-0.90

POSITIVE LOGITS

 this

3.02

 этом

1.81

 этого

1.57

 này

1.52

 цьому

1.48

 dette

1.42

これは

1.32

 Dette

1.25

 هذا

1.24

 detta

1.23

Activations Density 0.007%