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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating movement from one place to another

    oai_token-act-pair · gpt-3.5-turbo

    references to paths or journeys

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lishes
    -0.68
     actionGroup
    -0.65
    iston
    -0.65
     artif
    -0.64
    esson
    -0.60
    onom
    -0.60
     pse
    -0.59
     Artificial
    -0.59
    cons
    -0.58
    unn
    -0.58
    POSITIVE LOGITS
     home
    1.41
    packing
    0.98
    home
    0.97
     Home
    0.96
     HOME
    0.94
     downstairs
    0.92
     west
    0.89
     back
    0.87
     thence
    0.86
     north
    0.86
    Act Density 0.228%

    No Known Activations