Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    identifiers related to class definitions in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    
    -0.68
    UnusedPrivate
    -0.68
     chi̍t
    -0.65
    <caption>
    -0.60
    Спасылкі
    -0.58
     vivant
    -0.58
     jugé
    -0.58
    memoized
    -0.57
    таратура
    -0.55
    alucía
    -0.55
    POSITIVE LOGITS
     Class
    1.08
    class
    1.05
    Class
    1.00
     class
    0.89
     CLASS
    0.81
    Portale
    0.78
     classe
    0.73
    CLASS
    0.69
    ClassId
    0.68
    Classe
    0.62
    Act Density 0.054%

    No Known Activations