INDEX

Explanations

electric or electrical nouns

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

 electricity

-0.12

 elective

-0.11

 electrical

-0.11

 electrom

-0.11

/back

-0.10

inator

-0.10

 Electricity

-0.10

 electrodes

-0.10

lector

-0.10

 Electrical

-0.10

POSITIVE LOGITS

ally

0.33

ians

0.21

ALLY

0.18

idad

0.18

ian

0.18

ity

0.17

ityEngine

0.16

 thoáº¡i

0.16

ities

0.15

idade

0.15

Activations Density 0.032%