INDEX

Explanations

substantive points, questions, or legal

This neuron activates on occurrences of the word “substantive” or its morphological variants (i.e. the substring “substan–”).

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

are

-1.99

You

-1.98

</td>

-1.96

-1.88

 dañ

-1.82

ers

-1.80

The

-1.77

р

-1.74

Our

-1.72

ها

-1.71

POSITIVE LOGITS

喼

2.23

刧

2.16

?”

2.09

 substantive

2.08



1.95

èvent

1.90

蘼

1.89

 stället

1.81

 خاصی

1.80

</em>

1.77

Activations Density 0.007%