INDEX

Explanations

love to / grateful for expressions

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

 由于

1.46

 শ্রীযুক্ত

1.41

 여러분

1.38

 Bạn

1.34

saxophone

1.32

 제가

1.32

 voitures

1.31

 রাগ

1.31

 Sereth

1.29

 युवकों

1.29

POSITIVE LOGITS

 outright

0.89

 minimally

0.89

<0xE2>

0.85

unw

0.82

 even

0.82

 barely

0.79

––

0.79

off

0.78

at

0.76

 puțin

0.75

Activations Density 0.016%