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

    Neuronpedia

    INDEX
    Explanations

    references to homelessness

    oai_token-act-pair · gpt-3.5-turbo

    references to homelessness and related issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gran
    -0.79
    agall
    -0.76
     congr
    -0.72
    xit
    -0.72
    rees
    -0.69
    oys
    -0.68
    eq
    -0.67
    ioxide
    -0.67
     accur
    -0.66
    witz
    -0.65
    POSITIVE LOGITS
     encamp
    1.08
     homelessness
    0.99
     homeless
    0.96
     Homeless
    0.92
     Shelter
    0.86
     shelters
    0.86
     shelter
    0.80
     youths
    0.73
     Refugees
    0.73
    bage
    0.72
    Act Density 0.015%

    No Known Activations