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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating necessity or lack thereof, particularly in legal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AsUp
    -0.83
     Мексичка
    -0.81
    ViewFeatures
    -0.75
    Portale
    -0.74
    GEBURTSDATUM
    -0.72
    DeleteBehavior
    -0.67
    Rhestr
    -0.64
     @"/
    -0.64
     Roskov
    -0.63
    RegistryLite
    -0.63
    POSITIVE LOGITS
    不需要
    0.93
    无需
    0.83
    不用
    0.82
     needn
    0.80
    只需要
    0.72
     trenger
    0.72
    不必
    0.72
     hoeft
    0.69
     unnecessary
    0.67
    也不用
    0.67
    Act Density 0.263%

    No Known Activations