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

    Neuronpedia

    INDEX
    Explanations

    references to the United Nations Human Rights Council

    oai_token-act-pair · gpt-3.5-turbo

    references to human rights

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arella
    -0.75
     Rowling
    -0.69
    OHN
    -0.68
    onne
    -0.68
     ..........
    -0.67
    enegger
    -0.67
    rypt
    -0.67
     Reloaded
    -0.65
    heet
    -0.65
    è¦
    -0.65
    POSITIVE LOGITS
    itarian
    1.26
    itar
    1.06
     Rights
    1.01
    itary
    0.97
     beings
    0.90
    istic
    0.84
    rights
    0.83
    itaire
    0.81
    izational
    0.81
     rights
    0.81
    Act Density 0.015%

    No Known Activations