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

    Neuronpedia

    INDEX
    Explanations

    words containing the string "dom" followed by a numerical value

    oai_token-act-pair · gpt-3.5-turbo

    references to "domino" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    packing
    -0.81
    Quotes
    -0.78
    OPLE
    -0.76
    HCR
    -0.72
    ventory
    -0.71
    UGH
    -0.70
    WAYS
    -0.69
    VD
    -0.69
    FUL
    -0.68
    TING
    -0.68
    POSITIVE LOGITS
     dom
    0.94
    ially
    0.85
    ingen
    0.83
    iaries
    0.82
    loo
    0.80
    doms
    0.79
    iable
    0.78
    ials
    0.77
    itational
    0.77
    uin
    0.77
    Act Density 0.004%

    No Known Activations