INDEX

Explanations

unique and strange concepts

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

 речь

0.95

ted

0.87

+$

0.85

+{\

0.85

lua

0.82

ஜ்மஹால்

0.81

+,

0.81

risa

0.81

bmi

0.80

িয়ন

0.80

POSITIVE LOGITS

 juxtaposition

1.32

 juxt

1.26

 twist

1.17

 happenings

1.17

 occurrences

1.16

 Shaped

1.13

 shaped

1.11

occur

1.10

 perspective

1.10

 dichotomy

1.09

Activations Density 0.052%