INDEX

Explanations

Difference and possibility

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



0.37

psia

0.36

자리

0.35

说完

0.35

 кок

0.34

issons

0.34

bm

0.33

gung

0.33

ником

0.33

mentation

0.33

POSITIVE LOGITS

 Different

0.77

Different

0.76

 Possible

0.72

 different

0.71

 unexpectedly

0.71

Possible

0.70

 differently

0.69

 surprisingly

0.68

 remarkably

0.68

 Remarkably

0.66

Activations Density 0.068%