INDEX

Explanations

names and brands

The neuron is highly sensitive to references to organizations, institutions, or formal group names.

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

嗵

-1.63

 nastro

-1.59

 diing

-1.56

䊳

-1.51

 monstru

-1.48

 dedica

-1.47

 investir

-1.46

蠃

-1.44

 provar

-1.43

 trast

-1.41

POSITIVE LOGITS

↵↵

2.06

by

1.77

for

1.63

 still

1.57

all

1.47

 однако

1.43

 revital

1.34

 most

1.28

 liberal

1.28

an

1.27

Activations Density 0.087%