INDEX

Explanations

for a duration

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

to

-1.35

by

-1.27

 that

-1.26

only

-1.21

 certain

-1.18

 other

-1.15

 either

-1.15

new

-1.14

 only

-1.09

 particular

-1.01

POSITIVE LOGITS

 séjours

1.25

 phénom

1.23

 libéral

1.13

 toalha

1.12

 vuonna

1.11

在那里

1.09

 rembourse

1.09

 véhicules

1.07

 plongée

1.06

 familiale

1.05

Activations Density 0.026%