INDEX

Explanations

depression and suppression

The neuron selectively responds to words related to pressure or tension (e.g. containing roots like “press/pression” or “tensive”).

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

玫

-0.96

iju

-0.88

 incorporate

-0.86

дава

-0.84

 processes

-0.84

-0.82

 procedures

-0.80

 process

-0.80

in

-0.78

POSITIVE LOGITS



1.07

ileo

1.01

depress

0.97

 húmedo

0.97

 Baller

0.97

 Abingdon

0.94

 peuples

0.93

 Herpes

0.92

Че

0.91

 mögliche

0.91

Activations Density 0.055%