INDEX

Explanations

truck drivers and loads

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 deliberate

-0.10

 spor

-0.08

fell

-0.08

 hors

-0.07

unr

-0.07

bler

-0.07

 quelle

-0.07

archy

-0.07

rag

-0.07

rice

-0.07

POSITIVE LOGITS

loads

0.16

drivers

0.14

 drivers

0.14

 truck

0.14

 driver

0.13

ers

0.13

driver

0.13

 hauling

0.13

/bus

0.12

load

0.12

Activations Density 0.020%