INDEX

Explanations

knowing that

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

같이

0.36

mse

0.36

 heuristics

0.36

 excursion

0.35

mathspace

0.35

 leftWheel

0.35

 hydrology

0.34

ष्‍

0.34

 설정

0.34

 manually

0.34

POSITIVE LOGITS

 knowing

0.53

Knowing

0.52

 Knowing

0.47

knowing

0.42

 assured

0.42

thanks

0.38

 mengetahui

0.38

assured

0.38

 potrà

0.38

 díky

0.38

Activations Density 0.161%