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

    Neuronpedia

    INDEX
    Explanations

    keywords related to passengers or users, particularly in the context of transportation or travel

    oai_token-act-pair · gpt-3.5-turbo

    references to riders or participants in a transportation context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orial
    -0.75
    ritz
    -0.73
    argon
    -0.70
    aples
    -0.66
    otic
    -0.66
    mberg
    -0.65
    urated
    -0.64
     Crimea
    -0.63
    arial
    -0.61
    ilts
    -0.61
    POSITIVE LOGITS
    hip
    1.16
     riders
    1.05
     rider
    0.94
    bike
    0.89
    enty
    0.82
    pool
    0.78
    comed
    0.75
    mount
    0.74
    chairs
    0.74
     ride
    0.71
    Act Density 0.010%

    No Known Activations