INDEX

Explanations

visualization, memorable themes

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

 novelist

1.48

 escritor

1.38

 писатель

1.37

 działania

1.37

年も

1.34

 philosopher

1.34

ㄽ

1.33

 screenwriter

1.32

𝟎

1.32

 philosophers

1.31

POSITIVE LOGITS

म

1.12

weight

1.11

Smooth

1.08

prevent

1.03

cur

1.02

ankle

1.02

pro

1.00

hungry

0.98

కి

0.97

melting

0.96

Activations Density 0.000%