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

    Neuronpedia

    INDEX
    Explanations

    words related to racial or social segregation

    oai_token-act-pair · gpt-3.5-turbo

    terms related to segregation and communal divisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OTAL
    -0.77
    ODUCT
    -0.77
    rolog
    -0.76
    externalActionCode
    -0.76
    manship
    -0.74
    FORE
    -0.72
    odcast
    -0.72
    amina
    -0.70
    hao
    -0.69
    toe
    -0.68
    POSITIVE LOGITS
     segregation
    0.87
    gregation
    0.85
     coefficient
    0.85
    ized
    0.79
     riots
    0.78
    ization
    0.77
     choice
    0.77
     segreg
    0.77
    ised
    0.77
    arity
    0.76
    Act Density 0.044%

    No Known Activations