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

    Neuronpedia

    INDEX
    Explanations

    specific routes or route numbers

    oai_token-act-pair · gpt-3.5-turbo

    references to specific routes or pathways

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uster
    -0.91
    endi
    -0.82
    iaries
    -0.81
    luaj
    -0.79
     Hots
    -0.74
    usters
    -0.74
    oru
    -0.74
    ukes
    -0.72
    iary
    -0.71
    oat
    -0.71
    POSITIVE LOGITS
     routes
    1.02
    Route
    0.91
    finding
    0.90
     route
    0.88
    route
    0.86
     Roads
    0.80
    WAYS
    0.79
     Rout
    0.76
     routing
    0.75
    nels
    0.75
    Act Density 0.033%

    No Known Activations