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

    Neuronpedia

    INDEX
    Explanations

    verbs related to actions of discrimination, such as "discriminate," "harassed," "intimidated," "imprisoned," and "torture."

    oai_token-act-pair · gpt-3.5-turbo

    terms related to systemic discrimination and human rights violations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     PsyNet
    -0.89
    inventoryQuantity
    -0.85
    soType
    -0.84
     magnification
    -0.81
    ãĤ´ãĥ³
    -0.76
    forward
    -0.72
    soDeliveryDate
    -0.70
    hower
    -0.70
    wcsstore
    -0.67
    Setup
    -0.66
    POSITIVE LOGITS
     civilians
    1.48
     innocent
    1.34
     minorities
    1.32
     citizens
    1.23
     unarmed
    1.22
     Palestinians
    1.22
     foreigners
    1.18
     peasants
    1.12
     pedestrians
    1.11
     Africans
    1.11
    Act Density 0.327%

    No Known Activations