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

    Neuronpedia

    INDEX
    Explanations

    events or situations related to legal or criminal issues

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Haram
    -0.90
    anooga
    -0.75
    oos
    -0.73
    ierrez
    -0.69
    inburgh
    -0.68
    leck
    -0.68
    aque
    -0.66
     Drac
    -0.66
     hypocr
    -0.65
    aleb
    -0.65
    POSITIVE LOGITS
     Ukrain
    0.88
    pring
    0.87
     Ples
    0.86
     ago
    0.83
    iversary
    0.79
    ipolar
    0.76
     Ago
    0.71
    nd
    0.71
    flower
    0.71
    lies
    0.69
    Act Density 0.402%

    No Known Activations