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

    Neuronpedia

    INDEX
    Explanations

    references to roads and their conditions, such as building, upgrading, accessing, or closing them

    oai_token-act-pair · gpt-3.5-turbo

    references to roads and their conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ividual
    -0.86
    arians
    -0.77
    ority
    -0.76
    rator
    -0.71
     Wong
    -0.71
    yip
    -0.71
    andum
    -0.68
    iaries
    -0.67
    ucket
    -0.67
    illian
    -0.66
    POSITIVE LOGITS
    ways
    1.25
    blocks
    1.12
     roads
    1.05
     Roads
    0.99
     highways
    0.97
    block
    0.96
     arteries
    0.95
    road
    0.94
    side
    0.94
    lane
    0.89
    Act Density 0.025%

    No Known Activations