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

    Neuronpedia

    INDEX
    Explanations

    phrases related to immigration policies and procedures

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    velength
    -0.78
     Rolls
    -0.74
    idges
    -0.72
    yss
    -0.72
    wig
    -0.70
    Ü
    -0.70
     Shiv
    -0.70
    Offline
    -0.70
     Leicester
    -0.69
    oeuv
    -0.69
    POSITIVE LOGITS
     deported
    1.15
     deport
    1.15
     DACA
    1.15
     detention
    1.10
     immigrants
    1.09
     incarcer
    1.09
     immigration
    1.07
     Latino
    1.07
     incarcerated
    1.07
     Detention
    1.06
    Act Density 0.145%

    No Known Activations