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

    Neuronpedia

    INDEX
    Explanations

    words related to disasters or emergencies

    oai_token-act-pair · gpt-3.5-turbo

    references to disasters or crises, particularly those involving significant events or figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hovah
    -0.78
    erest
    -0.75
    ologne
    -0.74
    ahime
    -0.72
    IGH
    -0.72
    ering
    -0.71
    ensive
    -0.70
    ANY
    -0.68
    senal
    -0.67
    ers
    -0.66
    POSITIVE LOGITS
     Tycoon
    1.01
    ilee
    0.76
    iated
    0.71
     accelerator
    0.70
    board
    0.69
    isks
    0.69
    iate
    0.68
    lite
    0.68
     pudding
    0.68
    oute
    0.67
    Act Density 0.016%

    No Known Activations