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

    Neuronpedia

    INDEX
    Explanations

    mentions of violations related to international human rights laws

    oai_token-act-pair · gpt-3.5-turbo

    references to human rights issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Transcript
    -0.79
    forth
    -0.74
    xual
    -0.72
    rypt
    -0.69
    INO
    -0.68
    onne
    -0.68
     Krug
    -0.68
     Ack
    -0.67
    creen
    -0.66
    OHN
    -0.66
    POSITIVE LOGITS
    itar
    1.17
     beings
    1.16
    itarian
    1.09
     rights
    1.08
    istic
    1.06
    itary
    1.01
    istically
    0.99
     trafficking
    0.96
    izes
    0.92
    rights
    0.88
    Act Density 0.024%

    No Known Activations