INDEX

Explanations

can say, can create, can see

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

 jednak

1.55

 بلکه

1.52

또한

1.51

authier

1.48

래

1.46

 however

1.46

퀴

1.46

حق

1.44

وا

1.44

 نیز

1.44

POSITIVE LOGITS

 probably

1.56

 likely

1.46

 skyrock

1.37

 tends

1.35

往往

1.33

 disappearing

1.33

 invariably

1.33

 usually

1.31

 thường

1.30

 often

1.27

Activations Density 0.002%