INDEX

Explanations

differences and Gemma models

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

 \%$.

0.44

 Temperatura

0.44

 Hombre

0.43

чника

0.42

yside

0.41

 dilwale

0.41

चुअल

0.39

ropolitana

0.39

 ['(?

0.39

มาชิก

0.39

POSITIVE LOGITS

ο

0.41

 constituent

0.40

して

0.37

 atypical

0.37

CP

0.36

 etti

0.35

 degradation

0.35

 fray

0.35

早期

0.34

RP

0.33

Activations Density 0.000%