INDEX

Explanations

not necessarily qualifiers

New Auto-Interp

Configuration

Prompts (Dashboard)

238,145 prompts, 512 tokens each

Dataset (Dashboard)

lmsys + oasst1

Embeds

IFrame

Link

Negative Logits

It

0.60

Although

0.59

Interestingly

0.57

 अथवा

0.56

While

0.56

Since

0.56

Unfortunately

0.54

while

0.54

Instead

0.53

그리고

0.53

POSITIVE LOGITS

 ruthless

0.92

 worse

0.90

 disrespectful

0.87

 relentless

0.86

 selfish

0.86

 brutal

0.85

 more

0.85

 playful

0.83

 aggressive

0.82

 glamorous

0.82

Activations Density 0.137%

No Known Activations