INDEX

Explanations

model response indicator

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

的三

1.08

枨

1.03

 трех

1.02

 léka

0.99

<unused143>

0.96

 Среди

0.96

లంగాణ

0.95

囵

0.94

 случай

0.93

(?)

0.93

POSITIVE LOGITS

 wenn

1.22

 për

1.14

 के

1.12

 تے

1.11

 دے

1.11

Invoice

1.10

 buat

1.09

 نے

1.06

 nevertheless

1.05

 mixts

1.02

Activations Density 0.007%