INDEX

Explanations

curse, cursed, curses, spell, bewitched

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

</h3>

-1.78

簠

-1.73

}))

-1.65

・・・」

-1.59

⁓

-1.58

皞

-1.55

Ƞ

-1.55

oneof

-1.53

 nakalista

-1.52

contributed

-1.52

POSITIVE LOGITS

}$

1.60

↵

1.53

 向量

1.38

也

1.38

);

1.38

 también

1.36

 indivíduo

1.33

selbe

1.30

だね

1.30

 repeating

1.29

Activations Density 0.015%