INDEX

Explanations

with this

The neuron fires on the head words of abstract, explanatory or relational noun-phrases (e.g. “problem,” “habit,” “quote,” “aspects,” “look,” “associated”) that introduce prepositional relations (“with,” “of,” “to,” “for,” etc.).

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

 also

-2.03

for

-2.02

 into

-1.59

 quite

-1.55

 takes

-1.55

 time

-1.55

at

-1.53

 either

-1.51

ally

-1.49

 taking

-1.49

POSITIVE LOGITS

‘’

1.43

malı

1.42

 AFRICAN

1.37

 ORANGE

1.35

 begon

1.34

 BOSTON

1.30

Tiffany

1.29

joyed

1.27

 SUNDAY

1.26

 MICHIGAN

1.25

Activations Density 0.141%