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

    Neuronpedia

    INDEX
    Explanations

    mentions of homelessness or homeless individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to homelessness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the term "homeless"

    oai_token-act-pair · gpt-4-turbo
    New Auto-Interp
    Negative Logits
    gran
    -0.78
     congr
    -0.75
    agall
    -0.73
    ezvous
    -0.70
    oys
    -0.69
    ioxide
    -0.68
     magnification
    -0.67
    illary
    -0.67
     accur
    -0.66
     Saban
    -0.65
    POSITIVE LOGITS
     homeless
    1.10
     homelessness
    1.08
     Homeless
    1.08
     encamp
    0.98
     shelters
    0.92
    bage
    0.88
     Shelter
    0.86
     shelter
    0.86
     camping
    0.73
     Salvation
    0.72
    Act Density 0.014%

    No Known Activations