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

    Neuronpedia

    INDEX
    Explanations

    references to myths or mythological content

    oai_token-act-pair · gpt-3.5-turbo

    references to myths and mythological concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ennis
    -0.70
    iew
    -0.70
    ensitive
    -0.68
    onduct
    -0.67
    ouch
    -0.67
    arry
    -0.66
     deliveries
    -0.66
    burg
    -0.64
    Assistant
    -0.64
    ACC
    -0.64
    POSITIVE LOGITS
     myth
    3.71
     myths
    2.96
    Myth
    2.73
     Myth
    2.68
     mythology
    2.42
     legend
    1.86
     mythical
    1.83
     misconception
    1.78
     folklore
    1.74
     legends
    1.51
    Act Density 0.023%

    No Known Activations