INDEX

Explanations

describing traits and states

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

 amelyek

0.97

 które

0.87

containing

0.82

ங்களில்

0.80

 които

0.79

íticas

0.78

Containing

0.77

ንሽ

0.77

തമായ

0.73

它们

0.73

POSITIVE LOGITS

 arrogant

1.36

 charismatic

1.29

 personable

1.22

 always

1.21

 lovable

1.16

 incapable

1.15

 grumpy

1.15

 masterful

1.15

 diligent

1.13

 happiest

1.12

Activations Density 0.105%