INDEX

Explanations

No Explanations Found

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

0.64

 untuk

0.63

 bahwa

0.61

 για

0.61

YOU

0.59

 दुनिया

0.58

 نړ

0.57

保证

0.57

 نړۍ

0.56

䣼

0.56

POSITIVE LOGITS

 likewise

1.44

 similarly

1.37

 ebenfalls

1.34

Similarly

1.22

 също

1.16

 тоже

1.13

 également

1.10

 Similarly

1.10

Likewise

1.05

 također

1.05

Activations Density 0.805%

No Known Activations