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

    Neuronpedia

    INDEX
    Explanations

    references to asylum seekers

    oai_token-act-pair · gpt-3.5-turbo

    references to asylum seekers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ories
    -0.75
    UT
    -0.72
    IP
    -0.72
     IPM
    -0.70
     Shore
    -0.70
    ODE
    -0.70
    AST
    -0.68
    APS
    -0.67
    ival
    -0.66
    OD
    -0.66
    POSITIVE LOGITS
     seekers
    1.57
    seekers
    1.11
     seeker
    1.07
     claimants
    0.94
     applicants
    0.89
     seeking
    0.81
    anamo
    0.81
    eker
    0.79
     detainees
    0.77
     hikers
    0.77
    Act Density 0.017%

    No Known Activations