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

    Neuronpedia

    INDEX
    Explanations

    references to public transportation, specifically buses

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Martial
    -0.72
     Centauri
    -0.70
     marrow
    -0.69
    AFTA
    -0.64
     Christensen
    -0.63
    aneous
    -0.63
    theless
    -0.62
    uria
    -0.60
     Lauder
    -0.60
     magnification
    -0.59
    POSITIVE LOGITS
    loads
    1.25
    load
    1.13
    INESS
    0.98
    hel
    0.94
    boys
    0.90
    driver
    0.87
    drivers
    0.87
     passengers
    0.86
    inson
    0.85
    hy
    0.85
    Act Density 0.022%

    No Known Activations