INDEX

Explanations

return value or action

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

夠

2.64

可以

2.27

 Nós

2.22

 vitesses

2.14

रों

2.09

ió

2.08

𝗪

2.04

 convirtió

2.02

 predicated

1.99

iore

1.97

POSITIVE LOGITS

er

2.60

THUR

2.13

ر

2.11

nama

2.00

hythm

1.95

ν

1.88

 dalle

1.86

1.85

يء

1.85

 typedef

1.82

Activations Density 0.253%