INDEX

Explanations

in followed by types of rooms

The neuron fires strongly on occurrences of the phrase “walk-in.”

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

-2.08

 tika

-1.59

-1.52

 gider

-1.52

ction

-1.39

 Suomessa

-1.38

↵

-1.38

nye

-1.37

стям

-1.35



-1.34

POSITIVE LOGITS

 These

1.66

𓋼

1.64

𝘢

1.58

 besucht

1.56

获奖

1.53

 diterapkan

1.50

锛

1.48

 давления

1.47

 heridas

1.47

 aftermath

1.47

Activations Density 0.005%