INDEX

Explanations

en followed by French words

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

 nouve

-0.10

 plage

-0.10

Rog

-0.09

gue

-0.09

urf

-0.09

uds

-0.09

Rae

-0.09

 plaisir

-0.09

 rencontre

-0.09

cient

-0.09

POSITIVE LOGITS

vers

0.11

lever

0.11

 cascade

0.11

.wikipedia

0.11

 attendant

0.11

raci

0.11

rig

0.10

flamm

0.10

Ir

0.10

onces

0.10

Activations Density 0.036%