INDEX

Explanations

formatting and non-English words

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

in

1.27

€™

1.15

 doesn

1.10

≤

1.10

 situational

1.10

 provides

1.06

↵↵

1.05

on

1.05

ibration

1.04

『

1.04

POSITIVE LOGITS

 maravill

1.25

uatu

1.22

 nuestros

1.21

 Mamata

1.20

を起こ

1.19

 terrestre

1.18

<unused730>

1.17

 murió

1.16

 habíamos

1.14

 morreu

1.13

Activations Density 0.105%