INDEX

Explanations

epithelial cells

This neuron detects mentions of epithelial cells in scientific and medical texts.

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

an

-3.08

föra

-1.95

 said

-1.95

].

-1.89

-1.84

‘

-1.80

 have

-1.78

li

-1.77

注意事

-1.76

—

-1.75

POSITIVE LOGITS

锝

2.34

 prenez

2.34

 ""));

2.31



2.20

 acostumb

2.20

ORDON

2.20

</sub>

2.19

徧

2.19

</h3>

2.16

 respald

2.16

Activations Density 0.043%