INDEX

Explanations

specific occurrences and states

This neuron detects mentions of “true‐story” or biographical/historical film content (e.g., true stories, biopics, historical dramas).

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

="

-1.42

all

-1.29

 from

-1.27

向了

-1.25

my

-1.23

</em>

-1.20

õ

-1.16

this

-1.16

ias

-1.14

POSITIVE LOGITS

 değişik

1.55

 păr

1.45

 atacado

1.39

 eccellente

1.38

btnLogin

1.37

 sviluppo

1.37

or

1.34

óculos

1.33

 или

1.32

怎麼

1.32

Activations Density 0.321%