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

    Neuronpedia

    INDEX
    Explanations

    words related to attitudes

    oai_token-act-pair · gpt-3.5-turbo

    references to societal attitudes and perceptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bid
    -0.78
    gran
    -0.75
    ded
    -0.74
    MER
    -0.74
    avez
    -0.73
    addafi
    -0.71
    aman
    -0.70
    amaz
    -0.69
    icles
    -0.68
    amen
    -0.68
    POSITIVE LOGITS
     attitudes
    1.27
     attitude
    0.93
     guiActiveUn
    0.92
     toward
    0.80
    insula
    0.79
     incent
    0.79
    ocial
    0.79
     towards
    0.79
    yip
    0.79
    terness
    0.77
    Act Density 0.007%

    No Known Activations