INDEX

Explanations

throw out or away

The neuron activates on verbs and phrases that describe discarding or throwing things away (e.g. “throw away,” “toss out”).

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

-2.45

-2.03

-1.95

-1.84

 seiner

-1.80

-1.77

of

-1.73

ed

-1.68

ll

-1.66

POSITIVE LOGITS

⽌

1.92

colgante

1.77

----------

1.75



1.73

-------

1.67

謖

1.63

壜

1.61

pallet

1.60

蟷

1.59

 compromising

1.57

Activations Density 0.002%