INDEX

Explanations

risk identification and mitigation

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

1.39

ي

1.30

↵↵

1.25

<0x0D>

1.21

 براي

1.16

 في

1.15

 considerare

1.12

↵↵↵↵

1.11

 время

1.08

 الك

1.07

POSITIVE LOGITS

toxicity

1.20

ری

1.10

of

1.09

राबरी

1.09

ні

1.06

စိတ်အပိုင်း

1.06

𝘀

1.03

vascular

1.02

ructures

1.01

Activations Density 0.031%