INDEX

Explanations

all, everything, tutte, tout, todo

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

 cambiando

-2.44

-2.36

臜

-2.28

 dessa

-2.25

↵

-2.20

 também

-2.17

 totalmente

-2.16

ing

-2.13

 намного

-2.06

 slams

-2.05

POSITIVE LOGITS

 else

2.70

逡

2.48

玗

2.34

鴆

2.28

◔

2.27

縠

2.20

2.19

 ignite

2.17

 abide

2.11

 sensed

2.11

Activations Density 0.002%