INDEX

Explanations

manner of change and variation

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

 podrás

0.15

 cranes

0.15

iling

0.14

iking

0.14

rian

0.14

 fries

0.14

aka

0.14

 tarafından

0.14

 exudes

0.14

POSITIVE LOGITS

 differently

0.25

 itself

0.24

 horribly

0.24

 spectacularly

0.23

 wildly

0.22

 favorably

0.22

 quite

0.22

 uncontroll

0.21

起来

0.21

 linearly

0.21

Activations Density 0.171%