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

    Neuronpedia

    INDEX
    Explanations

    words related to unpacking or unburdening

    oai_token-act-pair · gpt-3.5-turbo

    words related to the concept of being unpacked or unburdened

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anwhile
    -0.87
     Nanto
    -0.77
     Lauder
    -0.77
     Rams
    -0.76
     Carbuncle
    -0.75
    cium
    -0.74
    SHIP
    -0.73
    姫
    -0.72
     Towards
    -0.71
     Mata
    -0.71
    POSITIVE LOGITS
    assuming
    0.94
    ishable
    0.93
     unp
    0.93
    rep
    0.90
    ashed
    0.90
    romising
    0.87
    un
    0.87
    ruly
    0.87
    illed
    0.85
    ainted
    0.84
    Act Density 0.014%

    No Known Activations