INDEX

Explanations

making sense

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

Hao

-0.09

tug

-0.09

ä½ľ

-0.09

'::

-0.08

 motors

-0.08

é£

-0.08

 impress

-0.08

ocab

-0.08

Explanation

-0.08

 Kata

-0.08

POSITIVE LOGITS

 sense

0.38

 sentido

0.24

 Sense

0.24

sense

0.24

Sense

0.22

ense

0.14

 sene

0.14

 perfect

0.14

 senses

0.11

scn

0.11

Activations Density 0.019%