INDEX

Explanations

possessive pronouns followed by nouns

The neuron strongly activates on English third-person pronouns and possessive pronouns (e.g. “their,” “his,” “her,” “it,” “he”).

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

mortem

-1.53

titial

-1.52

});

-1.45

})

-1.44

veröffentlichung

-1.38

 ſen

-1.32

 GOING

-1.30

訁

-1.30

recently

-1.29

}</

-1.27

POSITIVE LOGITS

 with

2.02

 first

1.66

by

1.65

 επίσης

1.48

”、“

1.47

 หลวง

1.46

oluzione

1.38

 Económica

1.37

tisgarh

1.30

 másik

1.30

Activations Density 0.104%