INDEX

Explanations

challenge against, indictment yet

The neuron fires most strongly on prominent event/action words (major verbs or nouns) that denote significant occurrences in the text.

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

。

-1.62

}$.

-1.58

-1.41

-1.38

».

-1.37

).

-1.36

।

-1.30

}.

-1.27

։

-1.24

°,

-1.23

POSITIVE LOGITS

つづく

1.09

 persön

1.05

 دقیقه

1.03

 zakon

1.03

 recientes

1.02

落ちて

1.02

就此

1.01

ilih

0.98

 today

0.98

 kürzlich

0.98

Activations Density 0.390%