INDEX

Explanations

wide range

The neuron activates on words that signal a broad range or variety, such as “wide,” “range,” “broad,” and “variety.”

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

์

0.98

ная

0.96

 cuad

0.94

ست

0.93

нда

0.92

ксе

0.92

らが

0.92

んにちは

0.91

 furlough

0.91

 confrontation

0.90

POSITIVE LOGITS

 macam

1.22

 Bets

1.13

 styles

1.09

BUCK

1.07

amani

1.05

}$,

1.05

 Styles

1.04

ゆる

1.03

 típus

1.02

 Sizes

1.01

Activations Density 0.154%