INDEX

Explanations

words starting with Ti

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

ii

-0.11

an

-0.10

 Mikhail

-0.09

iat

-0.09

ation

-0.09

 Unsafe

-0.09

eron

-0.09

oir

-0.09

cov

-0.09

alan

-0.09

POSITIVE LOGITS

 dioxide

0.11

erra

0.11

ivist

0.11

ssue

0.11

awan

0.10

empo

0.10

plate

0.10

ervers

0.10

angle

0.10

pton

0.10

Activations Density 0.052%