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

    Neuronpedia

    INDEX
    Explanations

    phrases related to transportation, specifically involving bikes and trains

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    cious
    -0.63
     capt
    -0.58
     acqu
    -0.58
     Ore
    -0.56
    BILITY
    -0.55
    interstitial
    -0.55
    iliar
    -0.55
     tyr
    -0.54
     heartbeat
    -0.54
    ery
    -0.54
    POSITIVE LOGITS
    fitted
    1.27
    stretched
    1.25
    ta
    1.13
    doors
    1.09
    door
    0.99
    wards
    0.98
    smart
    0.96
    casts
    0.91
    skirts
    0.89
    fitting
    0.89
    Act Density 0.093%

    No Known Activations