INDEX

Explanations

it is clear that

This neuron activates on the discourse marker “clear that,” i.e. occurrences of the word “clear” (often followed by “that”) signaling an emphatic assertion.

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

–

-2.03

 también

-1.92

 Also

-1.92

 также

-1.70

த்த

-1.60

珖

-1.60

Կ

-1.59

Also

-1.57

 Meanwhile

-1.57

 Occasionally

-1.55

POSITIVE LOGITS

 lèvres

1.54

 oreilles

1.47

 frère

1.45

 enjeux

1.41

the

1.34

 plads

1.30

 wasn

1.30

 décisions

1.30

 cykel

1.29

Activations Density 0.012%