INDEX

Explanations

string

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

Changes

0.47

 Changes

0.41

 CHANGES

0.40

changes

0.38

 Gave

0.38

 gave

0.37

Giving

0.37

手中

0.36



0.36

[]:

0.36

POSITIVE LOGITS

 sits

0.65

 encapsulates

0.65

 describes

0.60

 speaks

0.59

 explains

0.59

 expresses

0.57

 summarizes

0.57

 illustrates

0.57

 examines

0.57

 begs

0.55

Activations Density 0.004%