INDEX

Explanations

no followed by concepts

This neuron consistently picks up instances of the standalone word “No,” particularly at the start of statements indicating absence or negative findings.

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

also

-1.70

 ใน

-1.63

 sprüche

-1.58

 ALSO

-1.56

 also

-1.55

 في

-1.55

 membag

-1.49

𓋼

-1.47

$,

-1.47

Also

-1.45

POSITIVE LOGITS

哢

1.56

 нами

1.56

away

1.52

 flew

1.45

 knew

1.44

gemeester

1.41

had

1.39

trät

1.34

amaño

1.33

就已经

1.33

Activations Density 0.043%