INDEX

Explanations

sentences indicating the neuron detects statements expressing capacity or permission

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 permission

-1.27

 permitted

-1.26

 enabled

-1.19

 Permission

-1.13

permission

-1.11

 licence

-1.09

 permitting

-1.08

 Enabled

-1.05

permit

-1.05

 permiso

-1.05

POSITIVE LOGITS

 allows

0.73

 Allows

0.68

Населення

0.67

RenderAtEndOf

0.67

Allows

0.64

 Roskov

0.59

 cientí

0.58

contentLoaded

0.56

 CHtml

0.56

internalType

0.55

Activations Density 0.034%