INDEX

Explanations

folder containing

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

 occuring

0.39

 menjadikan

0.39

蹭

0.38

 व्याकरण

0.37

aminophen

0.36

vvvert

0.36

 memasuki

0.36

틈

0.36

炙

0.34

 ग्रा

0.34

POSITIVE LOGITS

 containing

2.64

 Containing

2.30

containing

2.25

 chứa

2.19

 contenant

2.17

Containing

2.16

 berisi

2.11

 contain

2.08

 contains

2.05

 содержа

1.91

Activations Density 0.140%