INDEX

Explanations

changing direction or scale

The neuron fires on dynamic verbs that describe movement or change along a scale (e.g. get, shrink, go, progress, decrease).

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

on

-1.62

all

-1.55

or

-1.55

-1.52

did

-1.51

by

-1.43

no

-1.42

 every

-1.41

 Anderson

-1.40

be

-1.38

POSITIVE LOGITS

፱

1.38

icto

1.38

 incluindo

1.38



1.38

etui

1.36

 than

1.36

 عوض

1.35

やっと

1.34

including

1.34

 blatant

1.34

Activations Density 0.040%