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

    Neuronpedia

    INDEX
    Explanations

    phrases related to immigration policies and actions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to immigration and undocumented individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    escent
    -0.76
    HY
    -0.75
    idges
    -0.75
    Nap
    -0.72
     enthusi
    -0.71
    sbm
    -0.69
    uner
    -0.68
    velength
    -0.68
     Moment
    -0.68
     Philips
    -0.68
    POSITIVE LOGITS
     DACA
    1.17
     visas
    1.14
     deported
    1.07
     visa
    1.02
     deport
    1.01
     detention
    1.00
    immigrant
    1.00
     citizenship
    0.99
     illegally
    0.97
     detainee
    0.97
    Act Density 0.159%

    No Known Activations