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

    Neuronpedia

    INDEX
    Explanations

    phrases related to immigration policy and programs

    oai_token-act-pair · gpt-3.5-turbo

    references to childhood-related policies and immigration issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    HY
    -0.76
     Winc
    -0.70
     SPL
    -0.70
    âĶĢâĶĢ
    -0.69
    æ©
    -0.69
     Sunder
    -0.69
    shed
    -0.68
    velength
    -0.68
    rown
    -0.68
    rawdownloadcloneembedreportprint
    -0.67
    POSITIVE LOGITS
     visas
    1.18
     DACA
    1.08
     visa
    1.02
    immigrant
    1.02
     deported
    1.01
     illegally
    1.00
     amnesty
    0.97
     ineligible
    0.96
     citizenship
    0.94
     immigrants
    0.91
    Act Density 0.201%

    No Known Activations