INDEX

Explanations

twitter, whisper, bitter

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

 وعلى

2.61

其他

1.98

یت

1.95

1.91

с

1.79

Message

1.64

 [&](

1.62

도

1.62

私募基金

1.61

 Перейти

1.59

POSITIVE LOGITS

lığ

2.86

lık

2.38

flox

2.31

lardan

2.28

lığı

2.23

führt

2.23

ar

2.22

tı

2.20

ोत्तर

2.19

që

2.17

Activations Density 0.232%