INDEX

Explanations

for X [beneficiary/purpose]

The neuron detects the “for” in general‐statement constructions like “it is important/desirable/imperative/appropriate for X to …,” i.e. phrases expressing necessity or desirability.

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

 secado

-1.70

噤

-1.64

 larges

-1.57

 móveis

-1.55

 colgantes

-1.53

 profondeur

-1.52

 drenaje

-1.51

はなく

-1.51

 ausreich

-1.50

 passende

-1.49

POSITIVE LOGITS

to

2.27

for

1.90

one

1.89

 will

1.79

two

1.73

if

1.71

by

1.70

and

1.68

 three

1.66

you

1.66

Activations Density 0.013%