INDEX

Explanations

I `I` `it` `you` `they` phrases

The neuron strongly activates on common English pronouns and related subject words (e.g. “I,” “it,” “they,” “are”).

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

これも

-1.52

↵

-1.35

 That

-1.34

or

-1.32

𝓾

-1.29

 ALWAYS

-1.28

こちらも

-1.28

–

-1.25

食べる

-1.22

 siempre

-1.21

POSITIVE LOGITS

 插画

1.55

枼

1.44

،

1.42

↗

1.38

：

1.34

 anún

1.34

 veja

1.28

》

1.27

 verhind

1.27

reportWebVitals

1.27

Activations Density 0.047%