INDEX

Explanations

plain language or text

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

ित

1.15

 mezzanine

0.89

Iterations

0.86

'$

0.85

elés

0.84

iete

0.83

'{

0.83

 якості

0.83

িস

0.82

 arada

0.82

POSITIVE LOGITS

clothes

1.48

spoken

1.30

 истины

1.27

ishment

1.18

tains

1.17

 vanilla

1.10

1.06

 باند

1.05

ት

1.05

tive

1.05

Activations Density 0.031%