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

    Neuronpedia

    INDEX
    Explanations

    mentions of roads or trips

    oai_token-act-pair · gpt-3.5-turbo

    references to roads and journeys

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    emort
    -0.79
    arians
    -0.75
    ividual
    -0.74
    ancial
    -0.74
     Wong
    -0.73
    illian
    -0.72
     Hots
    -0.71
    ermott
    -0.69
    uary
    -0.68
    ulu
    -0.68
    POSITIVE LOGITS
    trip
    1.15
    ways
    1.00
    blocks
    0.95
    fare
    0.92
    block
    0.91
    cycle
    0.88
    runner
    0.84
    maps
    0.83
    road
    0.82
    show
    0.82
    Act Density 0.022%

    No Known Activations