INDEX

Explanations

only in

This neuron detects occurrences of the word “only” when it introduces an exclusivity or restriction (e.g., “only in,” “only when,” “available only”).

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

-1.70

ers

-1.56

︲

-1.55

-1.32

AutoModerator

-1.30

 gratuite

-1.30

筈

-1.30

-1.28

lui

-1.27

ヌード

-1.26

POSITIVE LOGITS

 there

2.08

 those

2.06

 that

1.75

 their

1.70

if

1.63

 this

1.59

 these

1.56

for

1.52

ンドウ

1.50

 penyimpanan

1.45

Activations Density 0.086%