INDEX

Explanations

programming code/documentation

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 globally

-0.30

åħ¨çĲĥ

-0.29

åľ¨åħ¨åĽ½

-0.29

åħ¨åĽ½

-0.29

arsing

-0.29

 sampling

-0.28

åľ¨åħ¨çĲĥ

-0.28

ãĥĢãĥ³

-0.28

åħ¨æł¡

-0.28

æīĵåį°

-0.28

POSITIVE LOGITS

 sled

0.28

 package

0.26

 mounted

0.26

å¸¸

0.25

atatype

0.24

åĽ´è§Ĥ

0.24

packages

0.24

THING

0.24

 packages

0.24

ackage

0.24

Activations Density 0.904%