INDEX

Explanations

in the context of openings

The neuron strongly activates on the preposition “in,” especially where it introduces a locative or contextual phrase in technical/descriptive text.

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

 There

-1.68

now

-1.60

 That

-1.52

 here

-1.52

 Actually

-1.45

一说

-1.43

 znalaz

-1.40

there

-1.38

-1.37

-1.36

POSITIVE LOGITS

媵

1.63

耵

1.59

ᐢ

1.59

 malheureux

1.56

the

1.54

}$

1.51

那你

1.49

 vieux

1.48

quelize

1.45

șa

1.44

Activations Density 0.068%