INDEX

Explanations

data cleaning, machine learning, code generation

New Auto-Interp

Configuration

Prompts (Dashboard)

238,145 prompts, 512 tokens each

Dataset (Dashboard)

lmsys + oasst1

Embeds

IFrame

Link

Negative Logits

viel

1.42

गत

1.36

 djel

1.31

 plaie

1.22

 smooth

1.22

voren

1.22

ikker

1.22

WebApp

1.20

த்ரே

1.19

raw

1.17

POSITIVE LOGITS

 पहचा

1.55

erg

1.53

obs

1.41

onna

1.38

 Fahrer

1.36

 автоматы

1.35

chaften

1.35

oed

1.34

 автомат

1.33

 defaultstate

1.33

Activations Density 0.012%

No Known Activations