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

    Neuronpedia

    INDEX
    Explanations

    phrases related to inhumane treatment and violations of human rights

    oai_token-act-pair · gpt-3.5-turbo

    references related to human rights abuses and suffering in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cary
    -0.84
    bernatorial
    -0.79
    ramer
    -0.76
     ellipt
    -0.75
     Prediction
    -0.72
     Preferred
    -0.71
     Elect
    -0.70
    Elect
    -0.68
     js
    -0.67
     Pis
    -0.66
    POSITIVE LOGITS
     migrant
    1.16
     refugee
    1.03
     Refugees
    1.02
     refugees
    1.01
     detainees
    1.00
     laborers
    1.00
     garment
    0.99
     Rohingya
    0.99
     atrocities
    0.97
     migrants
    0.96
    Act Density 0.618%

    No Known Activations