INDEX

Explanations

comparative modifiers followed by comparatives

New Auto-Interp

Configuration

Prompts (Dashboard)

238,145 prompts, 512 tokens each

Dataset (Dashboard)

lmsys + oasst1

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 bessere

1.45

 гораздо

1.45

更大的

1.45

 höhere

1.43

 größer

1.36

更多的

1.36

更加

1.36

更高的

1.36

 훨씬

1.30

 längre

1.28

POSITIVE LOGITS

 friend

1.14

tr

0.94

lov

0.88

 dryer

0.84

 stead

0.82

 cris

0.81

 sever

0.80

 Friend

0.77

 prou

0.77

mer

0.77

Activations Density 0.522%