INDEX

Explanations

intelligence test scores

The neuron activates on numeric tokens (e.g. test scores, percentages, measurements).

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

گوشی

-1.43

 її

-1.34

}\

-1.30

și

-1.27

还不错

-1.23

larda

-1.13

 їх

-1.13

کیف

-1.13

 sidor

-1.12

 humaine

-1.10

POSITIVE LOGITS

𝗴

1.44

 häufigsten

1.36

要知道

1.30

 enfrentan

1.22

 envió

1.16

чне

1.16

 vermutlich

1.12

цуз

1.10

 gesagt

1.09

 często

1.09

Activations Density 0.039%