INDEX

Explanations

social psychology and relationships

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

of

-1.83

now

-1.66

if

-1.32

 until

-1.26

for

-1.25

 that

-1.22

 which

-1.22

is

-1.22

so

-1.17

to

-1.09

POSITIVE LOGITS

卣

1.45

 چیه

1.45

 gesagt

1.39

 pérdidas

1.38

 preescolar

1.30

 bandoulière

1.30

 večer

1.29

 Fähig

1.28

 навіть

1.27

 fatiga

1.27

Activations Density 0.450%

No Known Activations