INDEX

Explanations

literally / ad verbum

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

 somewhat

0.58

 besonderen

0.53

 Somewhat

0.51

一定的

0.50

 besondere

0.50

 certain

0.50

 troublesome

0.48

 keen

0.47

 eher

0.47

 தற்போது

0.46

POSITIVE LOGITS

 literalmente

0.96

 literally

0.95

literally

0.93

 addirittura

0.80

 Literally

0.80

 буквально

0.74

 даже

0.72

 десятки

0.69

 bahkan

0.68

 zelfs

0.67

Activations Density 0.059%