INDEX

Explanations

asking for specific examples

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

vät

1.45

Ovo

1.44

igy

1.44

uve

1.42

ेशा

1.41

avier

1.40

odan

1.36

imiter

1.35

 ठेवा

1.33

igr

1.33

POSITIVE LOGITS

芯

1.38

 앞으로

1.30

 throughout

1.27

的這個

1.26

 अंग

1.26

 tackled

1.24

 गुणनखंड

1.23

 나무

1.21

Coronavirus

1.20

嫨

1.19

Activations Density 0.629%