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

    Neuronpedia

    INDEX
    Explanations

    instances of human rights violations or atrocities

    oai_token-act-pair · gpt-3.5-turbo

    references to acts of violence and oppression, particularly against specific ethnic or social groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ´ãĥ³
    -0.91
     magnification
    -0.79
    istries
    -0.72
    inventoryQuantity
    -0.71
    umbledore
    -0.71
    izon
    -0.69
    wcsstore
    -0.68
    EStream
    -0.68
    INESS
    -0.67
    uliffe
    -0.67
    POSITIVE LOGITS
     innocent
    1.60
     civilians
    1.53
     innoc
    1.52
     unarmed
    1.38
     peasants
    1.32
     minorities
    1.28
     captives
    1.25
     Palestinians
    1.25
     unsuspecting
    1.25
     oppressed
    1.21
    Act Density 0.373%

    No Known Activations