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

    Neuronpedia

    INDEX
    Explanations

    phrases related to returning to a previous location

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to returning or going back to a previous location

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Trend
    -0.66
    esson
    -0.65
     Contra
    -0.65
    alogy
    -0.61
    iston
    -0.59
     Billion
    -0.58
    oso
    -0.57
     palms
    -0.56
    天
    -0.56
     @@
    -0.56
    POSITIVE LOGITS
    packing
    1.34
     home
    1.31
    home
    1.14
    packs
    0.97
     HOME
    0.87
    country
    0.87
     Home
    0.85
    east
    0.80
     residence
    0.79
    Home
    0.78
    Act Density 0.109%

    No Known Activations