INDEX

Explanations

by introducing actions

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

ته

0.29

ራሉ

0.27

را

0.25

راق

0.25

是

0.25

мо

0.25

martial

0.25

ίζουν

0.25

iciaire

0.25

ви

0.24

POSITIVE LOGITS

 oats

0.24

 bootstrapping

0.24

 ऑफ़

0.23

oclaw

0.23

 campes

0.21

configs

0.21

ó

0.21

LIN

0.21

'));

0.21

 லி

0.20

Activations Density 0.032%