INDEX

Explanations

respectively, alike, values

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ようで

1.55

 زیرا

1.53

 ويم

1.36

soi

1.35

くて

1.32

하거나

1.31

 meaning

1.31

 anyhow

1.30

くい

1.30

 نکن

1.29

POSITIVE LOGITS

 respectively

2.50

 respectivamente

2.48

respectively

2.20

 တို့

2.06

 각각

2.04

相结合

2.01

 respectivement

1.99

都很

1.94

都

1.93

共に

1.88

Activations Density 0.321%