INDEX

Explanations

instructions with steps

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

ে

2.80

fichier

2.61

een

2.53

yrs

2.50

ing

2.38

י

2.38

יות

2.34

 facendo

2.31

eh

2.30

POSITIVE LOGITS

MENTS

2.24

 установ

2.19

िया

2.17

 зави

2.15

 заболевания

2.13

н

2.12

ן

2.05

 раз

2.04

 cheek

2.00

 nargs

1.98

Activations Density 0.020%