INDEX

Explanations

Toshiba, Misty, ingress, outwardly, Mire

This neuron responds to capitalized proper nouns and named-entity tokens.

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

泐

-2.78

—

-2.47

 beide

-2.41

 тех

-2.27

 leur

-2.25

)):

-2.25

 werfen

-2.19

を行い

-2.17

 abend

-2.11

.],

-2.09

POSITIVE LOGITS

lossians

2.81

ſelves

2.72

骘

2.70

Ꮸ

2.67

);

2.58

</h3>

2.56

⼥

2.39

蠊

2.34

...");

2.31

 dekoratif

2.30

Activations Density 0.005%