INDEX

Explanations

known as

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

wa

-1.23

 apparence

-1.08

lineNumber

-1.02

 חיצוניים

-0.93

 capire

-0.92

do

-0.92

 évaluation

-0.92

ria

-0.92

Fernsehserie

-0.90

 fiel

-0.90

POSITIVE LOGITS

to

2.66

 Known

1.48

 known

1.32

 worldwide

1.29

 conhecido

1.14

 KNOWN

1.10

 dikenal

1.09

 bekannt

1.07

 quantity

1.05

known

1.04

Activations Density 0.053%