INDEX

Explanations

lead and its toxicity

New Auto-Interp

Top Features by Cosine Similarity

Configuration

Prompts (Dashboard)

10,000 prompts, 128 tokens each

Dataset (Dashboard)

lmsys/lmsys-chat-1m

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ilt

-0.11

 Nylon

-0.10

 ammonia

-0.10

ocl

-0.09

 Bened

-0.08

.Tensor

-0.08

estr

-0.08

ulary

-0.08

 Kunst

-0.08

 virus

-0.08

POSITIVE LOGITS

 Lead

0.30

 lead

0.29

Lead

0.26

lead

0.22

_lead

0.18

Pb

0.13

BLL

0.13

 exposure

0.13

 solder

0.13

IQ

0.12

Activations Density 0.025%