INDEX

Explanations

what it takes

The neuron detects uses of the verb “take” (including its inflected form “takes”) when followed by “to,” as in “take(s) to ….”

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

The

-1.90

ついに

-1.74

-1.73

㍑

-1.73

↓↓↓

-1.72

（

-1.69

ADORES

-1.69

涐

-1.68

-1.66

 saisons

-1.63

POSITIVE LOGITS

 también

1.89

to

1.82

 Además

1.80

 Aunque

1.77

Of

1.65

 Occasionally

1.63

 However

1.61

 upkeep

1.56

ついて

1.55

有害

1.53

Activations Density 0.006%