INDEX

Explanations

variance and difference

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

lesssim

0.40

రకు

0.39

 ಪು

0.38

 преимущественно

0.38

とにかく

0.38

압

0.38

 достоин

0.37

))^{

0.37

لق

0.36

ahu

0.36

POSITIVE LOGITS

 different

2.14

不同的

2.00

 diferente

1.99

 diferentes

1.95

 Different

1.91

different

1.91

 berbeda

1.88

Different

1.85

 différente

1.80

 farklı

1.73

Activations Density 0.912%